root@AI:/apool/llama.cpp# venv/bin/python convert_hf_to_gguf.py --outfile /bpool/ERNIE-4.5-300B-A47B-PT.gguf /bpool/ERNIE-4.5-300B-A47B-PT
INFO:hf-to-gguf:Loading model: ERNIE-4.5-300B-A47B-PT
WARNING:hf-to-gguf:Failed to load model config from /bpool/ERNIE-4.5-300B-A47B-PT: Loading /bpool/ERNIE-4.5-300B-A47B-PT requires you to execute the configuration file in that repo on your local machine. Make sure you have read the code there to avoid malicious use, then set the option `trust_remote_code=True` to remove this error.
WARNING:hf-to-gguf:Trying to load config.json instead
INFO:hf-to-gguf:Model architecture: Ernie4_5_MoeForCausalLM
WARNING:hf-to-gguf:Failed to load model config from /bpool/ERNIE-4.5-300B-A47B-PT: Loading /bpool/ERNIE-4.5-300B-A47B-PT requires you to execute the configuration file in that repo on your local machine. Make sure you have read the code there to avoid malicious use, then set the option `trust_remote_code=True` to remove this error.
WARNING:hf-to-gguf:Trying to load config.json instead
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:gguf: loading model weight map from 'model.safetensors.index.json'
INFO:hf-to-gguf:gguf: loading model part 'model-00001-of-00123.safetensors'
INFO:hf-to-gguf:token_embd.weight,            torch.bfloat16 --> F16, shape = {8192, 103424}
INFO:hf-to-gguf:blk.0.attn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.0.ffn_down.weight,        torch.bfloat16 --> F16, shape = {28672, 8192}
INFO:hf-to-gguf:blk.0.ffn_gate.weight,        torch.bfloat16 --> F16, shape = {8192, 28672}
INFO:hf-to-gguf:blk.0.ffn_up.weight,          torch.bfloat16 --> F16, shape = {8192, 28672}
INFO:hf-to-gguf:blk.0.ffn_norm.weight,        torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.0.attn_k.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.0.attn_output.weight,     torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.0.attn_q.weight,          torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.0.attn_v.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.1.attn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.1.ffn_down.weight,        torch.bfloat16 --> F16, shape = {28672, 8192}
INFO:hf-to-gguf:blk.1.ffn_gate.weight,        torch.bfloat16 --> F16, shape = {8192, 28672}
INFO:hf-to-gguf:blk.1.ffn_up.weight,          torch.bfloat16 --> F16, shape = {8192, 28672}
INFO:hf-to-gguf:blk.1.ffn_norm.weight,        torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.1.attn_output.weight,     torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00002-of-00123.safetensors'
INFO:hf-to-gguf:blk.1.attn_k.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.1.attn_q.weight,          torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.1.attn_v.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.2.attn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.2.ffn_down.weight,        torch.bfloat16 --> F16, shape = {28672, 8192}
INFO:hf-to-gguf:blk.2.ffn_gate.weight,        torch.bfloat16 --> F16, shape = {8192, 28672}
INFO:hf-to-gguf:blk.2.ffn_up.weight,          torch.bfloat16 --> F16, shape = {8192, 28672}
INFO:hf-to-gguf:blk.2.ffn_norm.weight,        torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.2.attn_k.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.2.attn_output.weight,     torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.2.attn_q.weight,          torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.2.attn_v.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.3.attn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00003-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00004-of-00123.safetensors'
INFO:hf-to-gguf:blk.3.ffn_gate_exps.weight,   torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.3.ffn_up_exps.weight,     torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.3.ffn_down_exps.weight,   torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.3.ffn_gate_inp.weight,    torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.3.exp_probs_b.bias,       torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.3.ffn_norm.weight,        torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.3.attn_k.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.3.attn_output.weight,     torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.3.attn_q.weight,          torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.3.attn_v.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.4.attn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00005-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00006-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00007-of-00123.safetensors'
INFO:hf-to-gguf:blk.4.ffn_gate_exps.weight,   torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.4.ffn_up_exps.weight,     torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.4.ffn_down_exps.weight,   torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.4.ffn_gate_inp.weight,    torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.4.exp_probs_b.bias,       torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.4.ffn_norm.weight,        torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.4.attn_k.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.4.attn_output.weight,     torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.4.attn_q.weight,          torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.4.attn_v.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.5.attn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00008-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00009-of-00123.safetensors'
INFO:hf-to-gguf:blk.5.ffn_gate_exps.weight,   torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.5.ffn_up_exps.weight,     torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.5.ffn_down_exps.weight,   torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.5.ffn_gate_inp.weight,    torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.5.exp_probs_b.bias,       torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.5.ffn_norm.weight,        torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.5.attn_k.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.5.attn_output.weight,     torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.5.attn_q.weight,          torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.5.attn_v.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.6.attn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00010-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00011-of-00123.safetensors'
INFO:hf-to-gguf:blk.6.ffn_gate_exps.weight,   torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.6.ffn_up_exps.weight,     torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.6.ffn_down_exps.weight,   torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.6.ffn_gate_inp.weight,    torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.6.exp_probs_b.bias,       torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.6.ffn_norm.weight,        torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.6.attn_k.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.6.attn_output.weight,     torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.6.attn_q.weight,          torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.6.attn_v.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.7.attn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00012-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00013-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00014-of-00123.safetensors'
INFO:hf-to-gguf:blk.7.ffn_gate_exps.weight,   torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.7.ffn_up_exps.weight,     torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.7.ffn_down_exps.weight,   torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.7.ffn_gate_inp.weight,    torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.7.exp_probs_b.bias,       torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.7.ffn_norm.weight,        torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.7.attn_k.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.7.attn_output.weight,     torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.7.attn_q.weight,          torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.7.attn_v.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.8.attn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00015-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00016-of-00123.safetensors'
INFO:hf-to-gguf:blk.8.ffn_gate_exps.weight,   torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.8.ffn_up_exps.weight,     torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.8.ffn_down_exps.weight,   torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.8.ffn_gate_inp.weight,    torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.8.exp_probs_b.bias,       torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.8.ffn_norm.weight,        torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.8.attn_k.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.8.attn_output.weight,     torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.8.attn_q.weight,          torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.8.attn_v.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.9.attn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00017-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00018-of-00123.safetensors'
INFO:hf-to-gguf:blk.10.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.9.ffn_gate_exps.weight,   torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.9.ffn_up_exps.weight,     torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.9.ffn_down_exps.weight,   torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.9.ffn_gate_inp.weight,    torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.9.exp_probs_b.bias,       torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.9.ffn_norm.weight,        torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.9.attn_k.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.9.attn_output.weight,     torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.9.attn_q.weight,          torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.9.attn_v.weight,          torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:gguf: loading model part 'model-00019-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00020-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00021-of-00123.safetensors'
INFO:hf-to-gguf:blk.10.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.10.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.10.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.10.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.10.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.10.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.10.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.10.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.10.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.10.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.11.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00022-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00023-of-00123.safetensors'
INFO:hf-to-gguf:blk.11.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.11.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.11.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.11.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.11.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.11.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.11.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.11.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.11.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.11.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.12.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00024-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00025-of-00123.safetensors'
INFO:hf-to-gguf:blk.12.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.12.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.12.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.12.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.12.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.12.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.12.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.12.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.12.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.12.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.13.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00026-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00027-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00028-of-00123.safetensors'
INFO:hf-to-gguf:blk.13.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.13.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.13.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.13.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.13.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.13.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.13.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.13.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.13.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.13.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.14.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00029-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00030-of-00123.safetensors'
INFO:hf-to-gguf:blk.14.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.14.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.14.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.14.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.14.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.14.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.14.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.14.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.14.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.14.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.15.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00031-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00032-of-00123.safetensors'
INFO:hf-to-gguf:blk.15.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.15.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.15.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.15.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.15.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.15.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.15.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00033-of-00123.safetensors'
INFO:hf-to-gguf:blk.15.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.15.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.15.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.16.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00034-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00035-of-00123.safetensors'
INFO:hf-to-gguf:blk.16.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.16.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.16.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.16.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.16.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.16.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.16.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.16.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.16.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.16.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.17.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00036-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00037-of-00123.safetensors'
INFO:hf-to-gguf:blk.17.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.17.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.17.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.17.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.17.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.17.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.17.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.17.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.17.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.17.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.18.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00038-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00039-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00040-of-00123.safetensors'
INFO:hf-to-gguf:blk.18.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.18.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.18.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.18.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.18.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.18.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.18.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.18.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.18.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.18.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.19.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00041-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00042-of-00123.safetensors'
INFO:hf-to-gguf:blk.19.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.19.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.19.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.19.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.19.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.19.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.19.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.19.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.19.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.19.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.20.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00043-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00044-of-00123.safetensors'
INFO:hf-to-gguf:blk.20.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.20.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.20.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.20.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.20.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.20.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.20.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.20.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.20.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.20.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.21.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00045-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00046-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00047-of-00123.safetensors'
INFO:hf-to-gguf:blk.21.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.21.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.21.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.21.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.21.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.21.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.21.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.21.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.21.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.21.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.22.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00048-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00049-of-00123.safetensors'
INFO:hf-to-gguf:blk.22.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.22.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.22.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.22.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.22.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.22.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.22.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.22.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.22.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.22.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.23.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00050-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00051-of-00123.safetensors'
INFO:hf-to-gguf:blk.23.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.23.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.23.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.23.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.23.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.23.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.23.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.23.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.23.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.23.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.24.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00052-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00053-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00054-of-00123.safetensors'
INFO:hf-to-gguf:blk.24.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.24.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.24.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.24.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.24.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.24.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.24.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.24.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.24.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.24.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.25.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00055-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00056-of-00123.safetensors'
INFO:hf-to-gguf:blk.25.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.25.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.25.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.25.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.25.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.25.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.25.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.25.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.25.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.25.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.26.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00057-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00058-of-00123.safetensors'
INFO:hf-to-gguf:blk.26.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.26.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.26.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.26.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.26.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.26.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.26.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.26.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.26.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.26.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.27.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00059-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00060-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00061-of-00123.safetensors'
INFO:hf-to-gguf:blk.27.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.27.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.27.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.27.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.27.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.27.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.27.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.27.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.27.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.27.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.28.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00062-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00063-of-00123.safetensors'
INFO:hf-to-gguf:blk.28.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.28.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.28.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.28.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.28.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.28.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.28.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.28.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.28.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.28.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.29.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00064-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00065-of-00123.safetensors'
INFO:hf-to-gguf:blk.29.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.29.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.29.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.29.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.29.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.29.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.29.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00066-of-00123.safetensors'
INFO:hf-to-gguf:blk.29.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.29.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.29.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.30.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00067-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00068-of-00123.safetensors'
INFO:hf-to-gguf:blk.30.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.30.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.30.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.30.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.30.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.30.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.30.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.30.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.30.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.30.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.31.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00069-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00070-of-00123.safetensors'
INFO:hf-to-gguf:blk.31.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.31.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.31.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.31.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.31.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.31.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.31.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.31.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.31.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.31.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.32.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00071-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00072-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00073-of-00123.safetensors'
INFO:hf-to-gguf:blk.32.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.32.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.32.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.32.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.32.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.32.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.32.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.32.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.32.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.32.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.33.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00074-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00075-of-00123.safetensors'
INFO:hf-to-gguf:blk.33.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.33.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.33.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.33.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.33.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.33.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.33.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.33.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.33.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.33.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.34.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00076-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00077-of-00123.safetensors'
INFO:hf-to-gguf:blk.34.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.34.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.34.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.34.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.34.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.34.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.34.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.34.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.34.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.34.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.35.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00078-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00079-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00080-of-00123.safetensors'
INFO:hf-to-gguf:blk.35.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.35.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.35.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.35.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.35.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.35.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.35.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.35.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.35.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.35.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.36.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00081-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00082-of-00123.safetensors'
INFO:hf-to-gguf:blk.36.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.36.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.36.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.36.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.36.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.36.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.36.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.36.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.36.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.36.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.37.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00083-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00084-of-00123.safetensors'
INFO:hf-to-gguf:blk.37.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.37.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.37.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.37.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.37.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.37.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.37.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.37.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.37.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.37.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.38.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00085-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00086-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00087-of-00123.safetensors'
INFO:hf-to-gguf:blk.38.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.38.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.38.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.38.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.38.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.38.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.38.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.38.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.38.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.38.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.39.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00088-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00089-of-00123.safetensors'
INFO:hf-to-gguf:blk.39.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.39.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.39.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.39.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.39.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.39.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.39.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.39.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.39.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.39.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.40.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00090-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00091-of-00123.safetensors'
INFO:hf-to-gguf:blk.40.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.40.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.40.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.40.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.40.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.40.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.40.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.40.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.40.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.40.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.41.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00092-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00093-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00094-of-00123.safetensors'
INFO:hf-to-gguf:blk.41.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.41.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.41.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.41.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.41.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.41.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.41.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.41.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.41.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.41.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.42.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00095-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00096-of-00123.safetensors'
INFO:hf-to-gguf:blk.42.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.42.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.42.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.42.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.42.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.42.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.42.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.42.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.42.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.42.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.43.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00097-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00098-of-00123.safetensors'
INFO:hf-to-gguf:blk.43.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.43.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.43.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.43.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.43.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.43.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.43.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00099-of-00123.safetensors'
INFO:hf-to-gguf:blk.43.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.43.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.43.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.44.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00100-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00101-of-00123.safetensors'
INFO:hf-to-gguf:blk.44.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.44.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.44.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.44.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.44.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.44.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.44.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.44.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.44.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.44.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.45.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00102-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00103-of-00123.safetensors'
INFO:hf-to-gguf:blk.45.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.45.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.45.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.45.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.45.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.45.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.45.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.45.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.45.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.45.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.46.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00104-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00105-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00106-of-00123.safetensors'
INFO:hf-to-gguf:blk.46.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.46.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.46.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.46.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.46.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.46.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.46.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.46.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.46.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.46.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.47.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00107-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00108-of-00123.safetensors'
INFO:hf-to-gguf:blk.47.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.47.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.47.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.47.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.47.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.47.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.47.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.47.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.47.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.47.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.48.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00109-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00110-of-00123.safetensors'
INFO:hf-to-gguf:blk.48.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.48.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.48.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.48.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.48.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.48.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.48.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.48.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.48.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.48.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.49.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00111-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00112-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00113-of-00123.safetensors'
INFO:hf-to-gguf:blk.49.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.49.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.49.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.49.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.49.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.49.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.49.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.49.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.49.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.49.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.50.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00114-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00115-of-00123.safetensors'
INFO:hf-to-gguf:blk.50.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.50.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.50.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.50.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.50.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.50.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.50.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.50.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.50.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.50.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.51.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00116-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00117-of-00123.safetensors'
INFO:hf-to-gguf:blk.51.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.51.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.51.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.51.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.51.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.51.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.51.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.51.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.51.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.51.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.52.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00118-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00119-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00120-of-00123.safetensors'
INFO:hf-to-gguf:blk.52.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.52.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.52.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.52.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.52.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.52.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.52.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.52.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.52.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.52.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.53.attn_norm.weight,      torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00121-of-00123.safetensors'
INFO:hf-to-gguf:gguf: loading model part 'model-00122-of-00123.safetensors'
INFO:hf-to-gguf:blk.53.ffn_gate_exps.weight,  torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.53.ffn_up_exps.weight,    torch.bfloat16 --> F16, shape = {8192, 3584, 64}
INFO:hf-to-gguf:blk.53.ffn_down_exps.weight,  torch.bfloat16 --> F16, shape = {3584, 8192, 64}
INFO:hf-to-gguf:blk.53.ffn_gate_inp.weight,   torch.float32 --> F32, shape = {8192, 64}
INFO:hf-to-gguf:blk.53.exp_probs_b.bias,      torch.float32 --> F32, shape = {64, 1}
INFO:hf-to-gguf:blk.53.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:blk.53.attn_k.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:blk.53.attn_output.weight,    torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.53.attn_q.weight,         torch.bfloat16 --> F16, shape = {8192, 8192}
INFO:hf-to-gguf:blk.53.attn_v.weight,         torch.bfloat16 --> F16, shape = {8192, 1024}
INFO:hf-to-gguf:output_norm.weight,           torch.bfloat16 --> F32, shape = {8192}
INFO:hf-to-gguf:gguf: loading model part 'model-00123-of-00123.safetensors'
INFO:hf-to-gguf:output.weight,                torch.bfloat16 --> F16, shape = {8192, 103424}
INFO:hf-to-gguf:Set meta model
INFO:hf-to-gguf:Set model parameters
INFO:hf-to-gguf:gguf: context length = 131072
INFO:hf-to-gguf:gguf: embedding length = 8192
INFO:hf-to-gguf:gguf: feed forward length = 28672
INFO:hf-to-gguf:gguf: head count = 64
INFO:hf-to-gguf:gguf: key-value head count = 8
INFO:hf-to-gguf:gguf: rope theta = 500000
INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-05
INFO:hf-to-gguf:gguf: file type = 1
WARNING:gguf.gguf_writer:Duplicated key name 'ernie4_5-moe.rope.freq_base', overwriting it with new value 500000 of type FLOAT32
INFO:hf-to-gguf:Set model quantization version
INFO:hf-to-gguf:Set model tokenizer
INFO:gguf.vocab:Setting special token type bos to 1
INFO:gguf.vocab:Setting special token type eos to 2
INFO:gguf.vocab:Setting special token type pad to 0
INFO:gguf.vocab:Setting chat_template to {%- if not add_generation_prompt is defined -%}
    {%- set add_generation_prompt = true -%}
{%- endif -%}
{%- if not cls_token is defined -%}
    {%- set cls_token = "<|begin_of_sentence|>" -%}
{%- endif -%}
{%- if not sep_token is defined -%}
    {%- set sep_token = "<|end_of_sentence|>" -%}
{%- endif -%}
{{- cls_token -}}
{%- for message in messages -%}
    {%- if message["role"] == "user" -%}
        {{- "User: " + message["content"] + "
" -}}
    {%- elif message["role"] == "assistant" -%}
        {{- "Assistant: " + message["content"] + sep_token -}}
    {%- elif message["role"] == "system" -%}
        {{- message["content"] + "
" -}}
    {%- endif -%}
{%- endfor -%}
{%- if add_generation_prompt -%}
    {{- "Assistant: " -}}
{%- endif -%}
INFO:gguf.gguf_writer:Writing the following files:
INFO:gguf.gguf_writer:/bpool/ERNIE-4.5-300B-A47B-PT.gguf: n_tensors = 591, total_size = 599.0G