|
/Users/Shared/Public/Github/llama.cpp/convert_hf_to_gguf.py --outtype bf16 . --outfile ./salamandra-2b_bf16.gguf |
|
INFO:hf-to-gguf:Loading model: |
|
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 part 'model.safetensors' |
|
INFO:hf-to-gguf:output.weight, torch.bfloat16 --> BF16, shape = {2048, 256000} |
|
INFO:hf-to-gguf:token_embd.weight, torch.bfloat16 --> BF16, shape = {2048, 256000} |
|
INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.0.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.0.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.0.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.0.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.0.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.0.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.0.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.1.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.1.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.1.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.1.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.1.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.1.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.1.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.1.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.10.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.10.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.10.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.10.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.10.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.10.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.10.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.10.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.11.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.11.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.11.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.11.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.11.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.11.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.11.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.11.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.12.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.12.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.12.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.12.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.12.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.12.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.12.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.12.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.13.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.13.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.13.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.13.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.13.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.13.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.13.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.13.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.14.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.14.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.14.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.14.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.14.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.14.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.14.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.14.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.15.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.15.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.15.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.15.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.15.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.15.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.15.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.15.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.16.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.16.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.16.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.16.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.16.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.16.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.16.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.16.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.17.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.17.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.17.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.17.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.17.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.17.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.17.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.17.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.18.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.18.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.18.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.18.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.18.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.18.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.18.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.18.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.19.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.19.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.19.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.19.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.19.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.19.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.19.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.19.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.2.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.2.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.2.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.2.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.2.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.2.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.2.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.2.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.20.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.20.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.20.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.20.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.20.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.20.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.20.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.20.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.21.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.21.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.21.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.21.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.21.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.21.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.21.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.21.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.22.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.22.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.22.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.22.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.22.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.22.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.22.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.22.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.23.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.23.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.23.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.23.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.23.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.23.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.23.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.23.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.3.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.3.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.3.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.3.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.3.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.3.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.3.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.3.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.4.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.4.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.4.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.4.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.4.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.4.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.4.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.4.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.5.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.5.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.5.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.5.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.5.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.5.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.5.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.5.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.6.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.6.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.6.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.6.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.6.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.6.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.6.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.6.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.7.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.7.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.7.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.7.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.7.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.7.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.7.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.7.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.8.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.8.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.8.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.8.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.8.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.8.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.8.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.8.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.9.ffn_down.weight, torch.bfloat16 --> BF16, shape = {5440, 2048} |
|
INFO:hf-to-gguf:blk.9.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.9.ffn_up.weight, torch.bfloat16 --> BF16, shape = {2048, 5440} |
|
INFO:hf-to-gguf:blk.9.ffn_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:blk.9.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.9.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.9.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:blk.9.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 2048} |
|
INFO:hf-to-gguf:output_norm.weight, torch.bfloat16 --> F32, shape = {2048} |
|
INFO:hf-to-gguf:Set meta model |
|
INFO:hf-to-gguf:Set model parameters |
|
INFO:hf-to-gguf:gguf: context length = 8192 |
|
INFO:hf-to-gguf:gguf: embedding length = 2048 |
|
INFO:hf-to-gguf:gguf: feed forward length = 5440 |
|
INFO:hf-to-gguf:gguf: head count = 16 |
|
INFO:hf-to-gguf:gguf: key-value head count = 16 |
|
INFO:hf-to-gguf:gguf: rope theta = 10000.0 |
|
INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-05 |
|
INFO:hf-to-gguf:gguf: file type = 32 |
|
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 unk to 0 |
|
INFO:gguf.vocab:Setting add_bos_token to True |
|
INFO:gguf.vocab:Setting add_eos_token to False |
|
INFO:hf-to-gguf:Set model quantization version |
|
INFO:gguf.gguf_writer:Writing the following files: |
|
INFO:gguf.gguf_writer:salamandra-2b_bf16.gguf: n_tensors = 219, total_size = 4.5G |
|
Writing: 100%|ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 4.51G/4.51G [00:10<00:00, 419Mbyte/s] |
|
INFO:hf-to-gguf:Model successfully exported to salamandra-2b_bf16.gguf |