{
  "metadata": {
    "total_parameters": 10653082624,
    "total_size": 11514432376
  },
  "weight_map": {
    "lm_head.weight": "model-00002-of-00002.safetensors",
    "model.encoder_hash_tok_embedding.weight": "model-00001-of-00002.safetensors",
    "model.global_transformer.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.10.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.11.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.12.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.13.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.16.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.17.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.18.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.19.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.2.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.20.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.21.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.22.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.23.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.25.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.26.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.27.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.28.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.29.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.3.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.30.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.31.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.4.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.5.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.6.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.7.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.8.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.layers.9.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.global_transformer.token_embedding_projection.weight": "model-00002-of-00002.safetensors",
    "model.global_transformer.token_embedding_projection.weight.absmax": "model-00002-of-00002.safetensors",
    "model.global_transformer.token_embedding_projection.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.global_transformer.token_embedding_projection.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.k_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.q_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.0.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.k_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.q_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.1.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.k_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.q_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.2.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.k_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.q_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.3.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.k_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.q_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.4.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.k_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.q_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.cross_attn_layers.5.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.2.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.3.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.4.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.layers.5.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_decoder.norm.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.patch_embedding_projection.weight": "model-00002-of-00002.safetensors",
    "model.local_decoder.patch_embedding_projection.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_decoder.patch_embedding_projection.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_decoder.patch_embedding_projection.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.k_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.q_norm.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_encoder.cross_attn_layers.0.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_encoder.embed_tokens.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_encoder.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.local_encoder.patch_embedding_projection.weight": "model-00002-of-00002.safetensors",
    "model.local_encoder.patch_embedding_projection.weight.absmax": "model-00002-of-00002.safetensors",
    "model.local_encoder.patch_embedding_projection.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.local_encoder.patch_embedding_projection.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.embed_tokens.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.10.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.11.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.12.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.13.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.2.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.3.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.4.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.5.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.6.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.7.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.8.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.mlp.down_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.mlp.down_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.mlp.gate_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.mlp.gate_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.mlp.up_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.mlp.up_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.k_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.k_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.o_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.o_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.q_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.q_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.v_proj.weight.absmax": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.v_proj.weight.quant_map": "model-00002-of-00002.safetensors",
    "model.patcher.layers.9.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
    "model.patcher.lm_head.weight": "model-00002-of-00002.safetensors",
    "model.patcher.norm.weight": "model-00002-of-00002.safetensors"
  }
}