add support for starcoder2 by cocoa-xu · Pull Request #5819 · ggml-org/llama.cpp

cocoa-xu · 2024-03-01T16:24:53Z

Hi this PR tries to add support for converting the recent released starcoder2 model to gguf format.

./convert-hf-to-gguf.py --outfile starcoder2-15b.bin --outtype f16 /Users/cocoa/Workspace/Git/starcoder2-15b

command output

Loading model: starcoder2-15b
gguf: This GGUF file is for Little Endian only
Set model parameters
Set model tokenizer
gguf: Adding 48872 merge(s).
gguf: Setting special token type bos to 0
gguf: Setting special token type eos to 0
gguf: Setting special token type unk to 0
Exporting model to 'starcoder2-15b.bin'
gguf: loading model part 'model-00001-of-00014.safetensors'
token_embd.weight, n_dims = 2, torch.float32 --> float16
blk.0.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.0.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.0.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.0.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.0.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.0.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.0.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.0.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.0.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.0.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.0.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.0.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.0.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.0.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.0.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.0.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.1.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.1.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.1.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.1.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.1.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.1.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.1.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.1.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.1.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.1.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.1.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.1.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.1.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.1.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.1.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.1.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.2.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.2.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.2.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.2.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.2.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.2.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.2.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.2.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00002-of-00014.safetensors'
blk.2.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.2.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.2.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.2.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.2.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.2.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.2.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.2.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.3.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.3.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.3.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.3.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.3.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.3.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.3.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.3.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.3.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.3.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.3.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.3.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.3.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.3.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.3.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.3.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.4.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.4.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.4.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.4.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.4.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.4.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.4.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.4.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.4.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.4.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.4.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.4.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.4.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.4.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.4.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.4.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.5.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.5.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.5.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.5.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.5.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.5.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.5.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.5.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00003-of-00014.safetensors'
blk.5.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.5.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.5.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.5.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.5.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.5.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.5.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.5.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.6.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.6.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.6.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.6.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.6.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.6.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.6.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.6.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.6.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.6.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.6.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.6.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.6.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.6.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.6.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.6.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.7.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.7.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.7.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.7.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.7.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.7.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.7.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.7.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.7.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.7.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.7.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.7.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.7.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.7.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.7.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.7.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.8.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.8.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.8.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.8.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.8.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.8.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.8.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.8.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00004-of-00014.safetensors'
blk.10.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.10.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.10.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.10.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.10.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.10.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.10.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.10.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.10.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.10.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.10.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.10.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.10.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.10.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.10.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.10.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.11.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.11.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.11.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.11.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.11.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.11.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.11.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.11.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.8.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.8.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.8.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.8.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.8.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.8.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.8.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.8.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.9.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.9.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.9.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.9.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.9.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.9.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.9.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.9.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.9.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.9.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.9.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.9.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.9.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.9.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.9.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.9.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00005-of-00014.safetensors'
blk.11.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.11.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.11.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.11.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.11.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.11.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.11.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.11.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.12.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.12.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.12.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.12.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.12.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.12.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.12.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.12.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.12.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.12.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.12.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.12.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.12.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.12.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.12.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.12.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.13.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.13.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.13.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.13.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.13.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.13.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.13.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.13.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.13.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.13.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.13.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.13.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.13.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.13.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.13.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.13.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.14.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.14.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.14.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.14.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.14.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.14.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.14.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.14.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00006-of-00014.safetensors'
blk.14.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.14.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.14.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.14.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.14.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.14.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.14.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.14.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.15.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.15.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.15.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.15.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.15.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.15.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.15.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.15.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.15.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.15.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.15.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.15.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.15.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.15.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.15.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.15.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.16.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.16.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.16.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.16.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.16.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.16.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.16.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.16.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.16.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.16.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.16.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.16.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.16.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.16.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.16.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.16.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.17.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.17.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.17.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.17.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.17.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.17.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.17.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.17.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00007-of-00014.safetensors'
blk.17.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.17.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.17.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.17.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.17.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.17.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.17.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.17.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.18.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.18.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.18.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.18.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.18.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.18.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.18.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.18.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.18.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.18.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.18.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.18.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.18.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.18.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.18.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.18.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.19.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.19.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.19.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.19.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.19.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.19.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.19.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.19.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.19.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.19.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.19.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.19.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.19.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.19.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.19.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.19.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.20.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.20.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.20.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.20.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.20.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.20.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.20.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.20.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00008-of-00014.safetensors'
blk.20.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.20.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.20.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.20.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.20.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.20.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.20.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.20.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.21.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.21.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.21.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.21.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.21.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.21.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.21.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.21.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.21.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.21.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.21.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.21.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.21.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.21.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.21.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.21.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.22.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.22.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.22.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.22.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.22.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.22.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.22.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.22.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.22.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.22.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.22.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.22.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.22.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.22.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.22.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.22.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.23.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.23.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.23.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.23.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.23.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.23.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.23.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.23.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00009-of-00014.safetensors'
blk.23.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.23.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.23.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.23.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.23.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.23.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.23.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.23.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.24.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.24.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.24.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.24.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.24.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.24.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.24.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.24.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.24.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.24.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.24.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.24.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.24.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.24.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.24.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.24.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.25.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.25.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.25.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.25.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.25.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.25.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.25.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.25.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.25.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.25.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.25.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.25.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.25.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.25.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.25.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.25.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.26.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.26.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.26.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.26.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.26.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.26.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.26.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.26.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00010-of-00014.safetensors'
blk.26.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.26.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.26.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.26.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.26.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.26.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.26.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.26.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.27.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.27.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.27.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.27.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.27.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.27.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.27.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.27.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.27.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.27.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.27.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.27.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.27.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.27.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.27.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.27.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.28.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.28.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.28.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.28.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.28.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.28.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.28.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.28.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.28.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.28.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.28.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.28.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.28.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.28.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.28.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.28.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.29.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.29.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.29.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.29.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.29.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.29.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.29.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.29.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00011-of-00014.safetensors'
blk.29.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.29.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.29.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.29.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.29.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.29.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.29.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.29.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.30.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.30.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.30.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.30.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.30.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.30.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.30.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.30.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.30.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.30.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.30.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.30.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.30.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.30.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.30.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.30.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.31.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.31.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.31.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.31.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.31.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.31.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.31.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.31.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.31.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.31.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.31.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.31.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.31.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.31.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.31.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.31.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.32.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.32.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.32.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.32.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.32.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.32.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.32.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.32.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00012-of-00014.safetensors'
blk.32.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.32.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.32.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.32.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.32.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.32.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.32.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.32.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.33.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.33.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.33.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.33.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.33.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.33.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.33.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.33.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.33.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.33.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.33.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.33.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.33.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.33.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.33.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.33.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.34.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.34.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.34.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.34.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.34.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.34.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.34.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.34.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.34.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.34.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.34.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.34.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.34.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.34.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.34.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.34.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.35.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.35.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.35.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.35.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.35.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.35.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.35.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.35.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00013-of-00014.safetensors'
blk.35.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.35.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.35.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.35.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.35.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.35.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.35.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.35.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.36.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.36.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.36.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.36.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.36.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.36.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.36.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.36.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.36.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.36.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.36.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.36.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.36.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.36.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.36.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.36.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.37.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.37.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.37.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.37.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.37.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.37.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.37.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.37.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.37.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.37.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.37.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.37.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.37.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.37.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.37.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.37.attn_v.weight, n_dims = 2, torch.float32 --> float16
blk.38.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.38.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.38.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.38.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.38.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.38.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.38.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.38.attn_v.weight, n_dims = 2, torch.float32 --> float16
gguf: loading model part 'model-00014-of-00014.safetensors'
output.weight, n_dims = 2, torch.float32 --> float16
blk.38.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.38.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.38.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.38.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.38.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.38.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.38.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.38.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.39.attn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.39.attn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.39.ffn_up.bias, n_dims = 1, torch.float32 --> float32
blk.39.ffn_up.weight, n_dims = 2, torch.float32 --> float16
blk.39.ffn_down.bias, n_dims = 1, torch.float32 --> float32
blk.39.ffn_down.weight, n_dims = 2, torch.float32 --> float16
blk.39.ffn_norm.bias, n_dims = 1, torch.float32 --> float32
blk.39.ffn_norm.weight, n_dims = 1, torch.float32 --> float32
blk.39.attn_k.bias, n_dims = 1, torch.float32 --> float32
blk.39.attn_k.weight, n_dims = 2, torch.float32 --> float16
blk.39.attn_output.bias, n_dims = 1, torch.float32 --> float32
blk.39.attn_output.weight, n_dims = 2, torch.float32 --> float16
blk.39.attn_q.bias, n_dims = 1, torch.float32 --> float32
blk.39.attn_q.weight, n_dims = 2, torch.float32 --> float16
blk.39.attn_v.bias, n_dims = 1, torch.float32 --> float32
blk.39.attn_v.weight, n_dims = 2, torch.float32 --> float16
output_norm.bias, n_dims = 1, torch.float32 --> float32
output_norm.weight, n_dims = 1, torch.float32 --> float32
Model successfully exported to 'starcoder2-15b.bin'

update

Sorry that I didn't notice that #5795 is already there.

add support for starcoder2

e8e6103

cocoa-xu closed this Mar 1, 2024

cocoa-xu deleted the cx/convert-starcoder2 branch March 1, 2024 16:26

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

add support for starcoder2#5819

add support for starcoder2#5819
cocoa-xu wants to merge 1 commit intoggml-org:masterfrom
cocoa-xu:cx/convert-starcoder2

cocoa-xu commented Mar 1, 2024 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Conversation

cocoa-xu commented Mar 1, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

update

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

cocoa-xu commented Mar 1, 2024 •

edited

Loading