python convert_hf_to_gguf.py --outtype bf16 F:\LLM\Austral-Xgen-Winton-9B

F:\LLM\Apps\llama.cpp>python convert_hf_to_gguf.py --outtype bf16 F:\LLM\Austral-Xgen-Winton-9B
INFO:hf-to-gguf:Loading model: Austral-Xgen-Winton-9B
INFO:hf-to-gguf:Model architecture: LlamaForCausalLM
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-00005.safetensors'
INFO:hf-to-gguf:token_embd.weight,           torch.bfloat16 --> BF16, shape = {4096, 102400}
INFO:hf-to-gguf:blk.0.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.0.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.0.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.0.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.0.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.0.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.0.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.0.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.0.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.1.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.1.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.1.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.1.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.1.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.1.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.1.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.1.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.1.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.2.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.2.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.2.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.2.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.2.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.2.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.2.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.2.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.2.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.3.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.3.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.3.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.3.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.3.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.3.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.3.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.3.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.3.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.4.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.4.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.4.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.4.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.4.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.4.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.4.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.4.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.4.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.5.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.5.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.5.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.5.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.5.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.5.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.5.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.5.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.5.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.6.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.6.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.6.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.6.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.6.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.6.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.6.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.6.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.6.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.7.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.7.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.7.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.7.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.7.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.7.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.7.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.7.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.7.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.8.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.8.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.8.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.8.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.8.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.8.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.8.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.8.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.8.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.9.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.9.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.9.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.9.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.9.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:gguf: loading model part 'model-00002-of-00005.safetensors'
INFO:hf-to-gguf:blk.10.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.10.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.10.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.10.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.10.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.10.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.10.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.10.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.10.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.11.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.11.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.11.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.11.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.11.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.11.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.11.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.11.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.11.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.12.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.12.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.12.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.12.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.12.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.12.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.12.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.12.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.12.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.13.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.13.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.13.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.13.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.13.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.13.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.13.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.13.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.13.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.14.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.14.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.14.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.14.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.14.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.14.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.14.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.14.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.14.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.15.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.15.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.15.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.15.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.15.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.15.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.15.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.15.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.15.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.16.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.16.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.16.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.16.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.16.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.16.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.16.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.16.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.16.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.17.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.17.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.17.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.17.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.17.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.17.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.17.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.17.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.17.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.18.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.18.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.18.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.18.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.18.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.18.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.18.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.18.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.18.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.19.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.19.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.19.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.19.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.19.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.19.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.19.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.19.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.19.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.20.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.20.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.20.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.20.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.20.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.20.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.9.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.9.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.9.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.9.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:gguf: loading model part 'model-00003-of-00005.safetensors'
INFO:hf-to-gguf:blk.20.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.20.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.20.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.21.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.21.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.21.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.21.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.21.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.21.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.21.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.21.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.21.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.22.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.22.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.22.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.22.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.22.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.22.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.22.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.22.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.22.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.23.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.23.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.23.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.23.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.23.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.23.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.23.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.23.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.23.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.24.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.24.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.24.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.24.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.24.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.24.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.24.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.24.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.24.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.25.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.25.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.25.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.25.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.25.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.25.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.25.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.25.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.25.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.26.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.26.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.26.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.26.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.26.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.26.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.26.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.26.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.26.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.27.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.27.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.27.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.27.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.27.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.27.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.27.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.27.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.27.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.28.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.28.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.28.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.28.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.28.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.28.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.28.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.28.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.28.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.29.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.29.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.29.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.29.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.29.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.29.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.29.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.29.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.29.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.30.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.30.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.30.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.30.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.30.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.30.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.30.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.30.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.30.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.31.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.31.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.31.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.31.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.31.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.31.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.31.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.31.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.31.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.32.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.32.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.32.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.32.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:gguf: loading model part 'model-00004-of-00005.safetensors'
INFO:hf-to-gguf:blk.32.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.32.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.32.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.32.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.32.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.33.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.33.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.33.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.33.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.33.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.33.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.33.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.33.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.33.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.34.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.34.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.34.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.34.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.34.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.34.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.34.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.34.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.34.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.35.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.35.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.35.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.35.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.35.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.35.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.35.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.35.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.35.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.36.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.36.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.36.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.36.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.36.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.36.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.36.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.36.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.36.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.37.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.37.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.37.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.37.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.37.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.37.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.37.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.37.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.37.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.38.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.38.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.38.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.38.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.38.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.38.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.38.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.38.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.38.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.39.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.39.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.39.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.39.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.39.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.39.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.39.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.39.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.39.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.40.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.40.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.40.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.40.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.40.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.40.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.40.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.40.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.40.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.41.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.41.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.41.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.41.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.41.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.41.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.41.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.41.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.41.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.42.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.42.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.42.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.42.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.42.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.42.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.42.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.42.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.42.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.43.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.43.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.43.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.43.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.43.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:gguf: loading model part 'model-00005-of-00005.safetensors'
INFO:hf-to-gguf:output.weight,               torch.bfloat16 --> BF16, shape = {4096, 102400}
INFO:hf-to-gguf:blk.43.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.43.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.43.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.43.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.44.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.44.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}
INFO:hf-to-gguf:blk.44.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.44.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}
INFO:hf-to-gguf:blk.44.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.44.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:blk.44.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.44.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}
INFO:hf-to-gguf:blk.44.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}
INFO:hf-to-gguf:output_norm.weight,          torch.bfloat16 --> F32, shape = {4096}
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 = 4096
INFO:hf-to-gguf:gguf: feed forward length = 14336
INFO:hf-to-gguf:gguf: head count = 32
INFO:hf-to-gguf:gguf: key-value head count = 8
INFO:hf-to-gguf:gguf: rope theta = 128000000
INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-06
INFO:hf-to-gguf:gguf: file type = 32
INFO:hf-to-gguf:Set model quantization version
INFO:hf-to-gguf:Set model tokenizer
Traceback (most recent call last):
  File "F:\LLM\Apps\llama.cpp\convert_hf_to_gguf.py", line 1865, in set_vocab
    self._set_vocab_sentencepiece()
  File "F:\LLM\Apps\llama.cpp\convert_hf_to_gguf.py", line 902, in _set_vocab_sentencepiece
    tokens, scores, toktypes = self._create_vocab_sentencepiece()
                               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "F:\LLM\Apps\llama.cpp\convert_hf_to_gguf.py", line 919, in _create_vocab_sentencepiece
    raise FileNotFoundError(f"File not found: {tokenizer_path}")
FileNotFoundError: File not found: F:\LLM\Austral-Xgen-Winton-9B\tokenizer.model

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "F:\LLM\Apps\llama.cpp\convert_hf_to_gguf.py", line 1868, in set_vocab
    self._set_vocab_llama_hf()
  File "F:\LLM\Apps\llama.cpp\convert_hf_to_gguf.py", line 997, in _set_vocab_llama_hf
    vocab = gguf.LlamaHfVocab(self.dir_model)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "F:\LLM\Apps\llama.cpp\gguf-py\gguf\vocab.py", line 488, in __init__
    raise FileNotFoundError('Cannot find Llama BPE tokenizer')
FileNotFoundError: Cannot find Llama BPE tokenizer

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "F:\LLM\Apps\llama.cpp\convert_hf_to_gguf.py", line 6560, in <module>
    main()
  File "F:\LLM\Apps\llama.cpp\convert_hf_to_gguf.py", line 6554, in main
    model_instance.write()
  File "F:\LLM\Apps\llama.cpp\convert_hf_to_gguf.py", line 404, in write
    self.prepare_metadata(vocab_only=False)
  File "F:\LLM\Apps\llama.cpp\convert_hf_to_gguf.py", line 517, in prepare_metadata
    self.set_vocab()
  File "F:\LLM\Apps\llama.cpp\convert_hf_to_gguf.py", line 1871, in set_vocab
    self._set_vocab_gpt2()
  File "F:\LLM\Apps\llama.cpp\convert_hf_to_gguf.py", line 844, in _set_vocab_gpt2
    special_vocab = gguf.SpecialVocab(self.dir_model, load_merges=True)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "F:\LLM\Apps\llama.cpp\gguf-py\gguf\vocab.py", line 43, in __init__
    self._load(Path(path))
  File "F:\LLM\Apps\llama.cpp\gguf-py\gguf\vocab.py", line 79, in _load
    self._try_load_from_tokenizer_json(path)
  File "F:\LLM\Apps\llama.cpp\gguf-py\gguf\vocab.py", line 171, in _try_load_from_tokenizer_json
    for processor in post_processor.get('processors', [post_processor]):
                     ^^^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'get'