INFO:hf-to-gguf:Loading model: source_model
INFO:hf-to-gguf:Model architecture: Qwen3_5MoeForConditionalGeneration
INFO:hf-to-gguf:gguf: loading model weight map from 'model.safetensors.index.json'
INFO:hf-to-gguf:gguf: indexing model part 'model-00001-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00002-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00003-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00004-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00005-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00006-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00007-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00008-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00009-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00010-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00011-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00012-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00013-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00014-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00015-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00016-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00017-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00018-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00019-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00020-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00021-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00022-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00023-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00024-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00025-of-00026.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00026-of-00026.safetensors'
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:token_embd.weight, torch.bfloat16 --> BF16, shape = {2048, 248320}
INFO:hf-to-gguf:blk.0.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.0.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.0.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.0.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.0.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.1.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.1.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.1.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.1.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.1.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.1.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.0.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.0.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.0.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.0.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.0.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.0.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.0.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.0.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.0.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.0.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.0.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.0.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.0.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.1.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.1.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.1.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.1.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.1.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.1.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.1.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.1.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.1.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.1.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.1.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.1.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.2.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.2.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.2.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.2.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.2.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.2.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.2.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.2.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.2.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.2.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.2.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.2.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.2.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.2.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.2.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.2.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.2.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.2.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.3.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.3.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.3.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.3.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.3.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.3.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.3.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.3.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.3.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.3.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.3.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.3.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.3.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.3.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.3.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.4.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.4.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.4.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.4.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.4.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.4.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.4.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.4.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.4.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.4.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.4.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.4.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.4.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.4.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.4.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.4.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.4.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.4.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.5.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.5.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.5.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.5.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.5.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.5.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.5.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.5.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.5.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.5.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.5.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.5.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.5.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.5.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.5.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.5.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.5.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.5.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.6.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.6.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.6.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.6.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.6.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.6.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.6.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.6.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.6.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.6.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.6.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.6.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.6.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.6.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.6.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.6.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.6.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.6.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.7.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.7.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.7.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.7.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.7.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.7.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.7.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.7.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.7.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.7.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.7.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.7.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.7.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.7.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.7.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.10.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.10.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.10.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.10.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.8.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.8.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.8.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.8.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.8.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.8.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.9.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.9.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.9.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.9.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.9.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.9.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.10.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.10.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.10.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.10.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.10.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.10.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.10.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.10.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.10.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.10.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.10.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.10.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.10.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.10.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.8.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.8.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.8.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.8.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.8.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.8.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.8.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.8.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.8.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.8.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.8.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.8.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.9.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.9.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.9.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.9.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.9.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.9.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.9.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.9.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.9.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.9.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.9.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.9.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.11.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.11.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.11.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.11.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.11.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.11.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.12.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.12.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.12.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.12.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.12.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.13.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.13.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.13.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.13.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.13.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.13.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.11.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.11.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.11.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.11.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.11.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.11.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.11.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.11.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.11.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.12.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.12.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.12.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.12.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.12.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.12.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.12.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.12.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.12.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.12.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.12.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.12.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.12.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.13.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.13.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.13.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.13.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.13.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.13.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.13.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.13.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.13.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.13.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.13.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.13.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.14.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.14.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.14.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.14.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.14.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.14.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.15.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.15.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.15.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.15.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.15.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.15.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.16.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.16.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.16.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.16.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.16.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.14.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.14.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.14.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.14.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.14.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.14.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.14.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.14.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.14.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.14.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.14.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.14.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.15.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.15.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.15.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.15.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.15.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.15.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.15.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.15.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.15.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.16.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.16.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.16.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.16.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.16.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.16.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.16.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.16.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.16.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.16.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.16.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.16.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.16.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.17.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.17.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.17.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.17.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.17.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.17.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.18.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.18.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.18.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.18.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.19.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.19.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.19.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.19.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.19.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.19.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.17.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.17.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.17.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.17.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.17.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.17.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.17.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.17.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.17.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.17.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.17.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.17.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.18.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.18.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.18.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.18.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.18.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.18.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.18.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.18.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.18.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.18.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.18.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.18.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.18.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.18.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.19.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.19.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.19.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.19.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.19.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.19.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.19.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.19.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.19.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.20.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.20.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.20.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.20.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.20.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.20.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.21.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.21.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.21.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.21.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.22.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.22.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.22.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.22.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.22.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.20.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.20.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.20.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.20.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.20.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.20.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.20.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.20.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.20.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.20.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.20.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.20.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.21.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.21.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.21.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.21.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.21.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.21.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.21.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.21.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.21.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.21.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.21.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.21.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.21.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.21.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.22.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.22.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.22.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.22.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.22.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.22.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.22.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.22.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.22.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.22.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.22.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.22.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.22.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.23.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.23.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.23.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.23.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.23.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.23.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.23.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.24.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.24.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.24.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.24.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.24.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.24.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.25.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.25.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.25.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.25.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.23.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.23.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.23.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.23.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.23.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.23.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.23.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.23.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.24.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.24.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.24.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.24.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.24.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.24.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.24.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.24.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.24.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.24.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.24.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.24.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.24.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.25.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.25.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.25.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.25.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.25.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.25.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.25.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.25.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.25.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.25.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.25.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.25.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.25.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.25.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.25.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.26.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.26.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.26.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.26.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.26.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.27.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.27.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.27.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.27.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.27.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.27.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.28.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.28.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.28.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.28.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.28.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.28.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.26.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.26.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.26.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.26.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.26.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.26.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.26.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.26.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.26.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.26.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.26.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.26.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.26.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.26.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.27.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.27.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.27.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.27.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.27.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.27.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.27.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.27.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.27.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.27.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.28.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.28.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.28.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.28.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.28.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.28.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.28.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.28.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.28.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.28.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.28.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.28.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.28.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.29.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.29.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.29.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.29.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.30.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.30.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.30.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.30.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.30.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.31.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.31.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.31.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.31.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.31.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.31.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.31.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.29.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.29.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.29.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.29.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.29.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.29.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.29.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.29.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.29.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.29.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.29.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.29.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.29.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.29.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.29.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.30.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.30.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.30.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.30.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.30.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.30.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.30.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.30.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.30.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.30.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.30.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.30.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.30.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.30.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.31.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.31.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.31.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.31.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.31.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.31.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.31.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.31.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.31.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.32.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.32.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.32.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.32.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.32.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.32.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.32.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.32.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.32.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.32.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.32.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.32.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.32.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.32.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.32.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.32.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.32.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.32.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.32.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.33.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.33.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.33.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.33.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.33.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.33.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.33.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.33.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.33.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.33.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.33.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.33.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.33.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.33.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.33.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.33.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.33.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.33.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.33.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.34.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.34.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.34.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.34.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.34.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.34.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.34.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.34.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.34.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.34.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.34.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.34.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.34.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.34.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.34.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.34.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.34.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.34.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.34.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.35.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.35.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.35.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.35.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.35.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.35.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.35.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.35.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.35.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.35.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.35.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.35.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.35.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.35.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.35.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.35.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.36.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.36.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.36.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.36.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.36.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.36.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.36.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.36.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.36.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.36.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.36.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.36.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.36.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.36.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.36.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.36.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.36.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.36.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.36.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.37.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.37.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.37.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.37.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.37.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.37.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.37.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.37.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.37.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.37.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.37.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.37.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.37.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.37.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.37.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.37.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.37.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.37.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.37.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.38.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.38.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.38.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.38.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.38.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.38.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.38.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.38.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.38.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.38.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.38.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.38.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.38.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.38.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.38.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.38.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.38.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.38.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.38.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.39.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.39.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:output.weight, torch.bfloat16 --> BF16, shape = {2048, 248320}
INFO:hf-to-gguf:blk.39.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.39.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.39.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.39.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.39.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.39.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.39.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.39.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.39.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.39.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.39.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.39.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.39.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.39.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:output_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:Set meta model
INFO:hf-to-gguf:Set model parameters
INFO:hf-to-gguf:gguf: context length = 262144
INFO:hf-to-gguf:gguf: embedding length = 2048
INFO:hf-to-gguf:gguf: head count = 16
INFO:hf-to-gguf:gguf: key-value head count = 2
WARNING:hf-to-gguf:Unknown RoPE type: default
INFO:hf-to-gguf:gguf: rope scaling type = NONE
INFO:hf-to-gguf:gguf: mrope sections: [11, 11, 10, 0]
INFO:hf-to-gguf:gguf: rope theta = 10000000
INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-06
INFO:hf-to-gguf:gguf: expert count = 256
INFO:hf-to-gguf:gguf: experts used count = 8
INFO:hf-to-gguf:gguf: file type = 32
INFO:hf-to-gguf:gguf: expert feed forward length = 512
INFO:hf-to-gguf:gguf: expert shared feed forward length = 512
INFO:hf-to-gguf:Set model quantization version
INFO:hf-to-gguf:Set model tokenizer
INFO:gguf.vocab:Adding 247587 merge(s).
INFO:gguf.vocab:Setting special token type eos to 248046
INFO:gguf.vocab:Setting special token type pad to 248044
INFO:gguf.vocab:Setting special token type bos to 248044
INFO:gguf.vocab:Setting add_bos_token to False
INFO:gguf.vocab:Setting chat_template to {%- set image_count = namespace(value=0) %}
{%- set video_count = namespace(value=0) %}
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
{%- if content is string %}
{{- content }}
{%- elif content is iterable and content is not mapping %}
{%- for item in content %}
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain images.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set image_count.value = image_count.value + 1 %}
{%- endif %}
{%- if add_vision_id %}
{{- 'Picture ' ~ image_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
{%- elif 'video' in item or item.type == 'video' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain videos.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set video_count.value = video_count.value + 1 %}
{%- endif %}
{%- if add_vision_id %}
{{- 'Video ' ~ video_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
{%- elif 'text' in item %}
{{- item.text }}
{%- else %}
{{- raise_exception('Unexpected item type in content.') }}
{%- endif %}
{%- endfor %}
{%- elif content is none or content is undefined %}
{{- '' }}
{%- else %}
{{- raise_exception('Unexpected content type.') }}
{%- endif %}
{%- endmacro %}
{%- if not messages %}
{{- raise_exception('No messages provided.') }}
{%- endif %}
{%- if tools and tools is iterable and tools is not mapping %}
{{- '<|im_start|>system\n' }}
{{- "# Tools\n\nYou have access to the following functions:\n\n" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n" }}
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }}
{%- if messages[0].role == 'system' %}
{%- set content = render_content(messages[0].content, false, true)|trim %}
{%- if content %}
{{- '\n\n' + content }}
{%- endif %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- else %}
{%- if messages[0].role == 'system' %}
{%- set content = render_content(messages[0].content, false, true)|trim %}
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" %}
{%- set content = render_content(message.content, false)|trim %}
{%- if not(content.startswith('') and content.endswith('')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if ns.multi_step_tool %}
{{- raise_exception('No user query found in messages.') }}
{%- endif %}
{%- for message in messages %}
{%- set content = render_content(message.content, true)|trim %}
{%- if message.role == "system" %}
{%- if not loop.first %}
{{- raise_exception('System message must be at the beginning.') }}
{%- endif %}
{%- elif message.role == "user" %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '' in content %}
{%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %}
{%- set content = content.split('')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- set reasoning_content = reasoning_content|trim %}
{%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
{{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{%- if loop.first %}
{%- if content|trim %}
{{- '\n\n\n\n' }}
{%- else %}
{{- '\n\n' }}
{%- endif %}
{%- else %}
{{- '\n\n\n' }}
{%- endif %}
{%- if tool_call.arguments is defined %}
{%- for args_name, args_value in tool_call.arguments|items %}
{{- '\n' }}
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
{{- args_value }}
{{- '\n\n' }}
{%- endfor %}
{%- endif %}
{{- '\n' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.previtem and loop.previtem.role != "tool" %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n\n' }}
{{- content }}
{{- '\n' }}
{%- if not loop.last and loop.nextitem.role != "tool" %}
{{- '<|im_end|>\n' }}
{%- elif loop.last %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- else %}
{{- raise_exception('Unexpected message role.') }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '\n\n\n\n' }}
{%- else %}
{{- '\n' }}
{%- endif %}
{%- endif %}
INFO:gguf.gguf_writer:Writing the following files:
INFO:gguf.gguf_writer:/tmp/q_quant_work/main.bf16.gguf: n_tensors = 733, total_size = 69.4G
Writing: 0%| | 0.00/69.4G [00:00