Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

add support for starcoder2 #5819

Closed
wants to merge 1 commit into from
Closed

add support for starcoder2 #5819

wants to merge 1 commit into from

Conversation

cocoa-xu
Copy link

@cocoa-xu cocoa-xu commented Mar 1, 2024 •
edited
Loading

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.

@cocoa-xu cocoa-xu closed this Mar 1, 2024
@cocoa-xu cocoa-xu deleted the cx/convert-starcoder2 branch March 1, 2024 16:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@cocoa-xu