{ "metadata": { "total_size": 4823743104 }, "weight_map": { "fc.weight": "model-00001-of-00005.safetensors", "hidden_norm.weight": "model-00001-of-00005.safetensors", "layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "layers.0.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors", "layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", "layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "layers.0.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", "layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "layers.0.self_attn.sinks": "model-00001-of-00005.safetensors", "layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "layers.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "layers.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "layers.1.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "layers.1.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", "layers.1.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", "layers.1.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "layers.1.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "layers.1.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", "layers.1.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "layers.1.self_attn.sinks": "model-00002-of-00005.safetensors", "layers.1.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "layers.2.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", "layers.2.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", "layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "layers.2.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", "layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "layers.2.self_attn.sinks": "model-00002-of-00005.safetensors", "layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "layers.3.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "layers.3.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "layers.3.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "layers.3.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", "layers.3.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", "layers.3.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "layers.3.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "layers.3.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", "layers.3.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "layers.3.self_attn.sinks": "model-00003-of-00005.safetensors", "layers.3.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "layers.4.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "layers.4.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "layers.4.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "layers.4.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "layers.4.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", "layers.4.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", "layers.4.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "layers.4.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "layers.4.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", "layers.4.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "layers.4.self_attn.sinks": "model-00003-of-00005.safetensors", "layers.4.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "layers.5.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "layers.5.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "layers.5.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "layers.5.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "layers.5.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", "layers.5.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", "layers.5.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "layers.5.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "layers.5.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", "layers.5.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "layers.5.self_attn.sinks": "model-00004-of-00005.safetensors", "layers.5.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "layers.6.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "layers.6.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "layers.6.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "layers.6.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "layers.6.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", "layers.6.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", "layers.6.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "layers.6.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "layers.6.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", "layers.6.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "layers.6.self_attn.sinks": "model-00004-of-00005.safetensors", "layers.6.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "layers.7.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "layers.7.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", "layers.7.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", "layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "layers.7.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", "layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "layers.7.self_attn.sinks": "model-00005-of-00005.safetensors", "layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "mask_embed": "model-00005-of-00005.safetensors", "norm.weight": "model-00005-of-00005.safetensors" } }