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.

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

Refactoring convert-pth-to-ggml.py: more concise and readable #109

Merged
merged 6 commits into from
Mar 19, 2023

Conversation

qunash
Copy link
Contributor

@qunash qunash commented Mar 14, 2023

No description provided.

@qunash qunash changed the title Refactoring: more concise and readable Refactoring convert-pth-to-ggml.py: more concise and readable Mar 14, 2023
@SuajCarrot
Copy link
Contributor

Exactly what I was thinking, however I think a better approach regarding string concatenation for paths is using os.path.join instead simply to avoid typos either by the user or the programmer if the code changes in the future. Overall, LGTM.

@gjmulder gjmulder added the duplicate This issue or pull request already exists label Mar 18, 2023
@ggerganov ggerganov merged commit 467b149 into ggml-org:master Mar 19, 2023
@ggerganov
Copy link
Member

ggerganov commented Mar 19, 2023

@SuajCarrot

I get this error:

python3 convert-pth-to-ggml.py models/7B/ 1
{'dim': 4096, 'multiple_of': 256, 'n_heads': 32, 'n_layers': 32, 'norm_eps': 1e-06, 'vocab_size': -1}
n_parts = 1

Processing part 0

Processing variable: tok_embeddings.weight with shape: torch.Size([32000, 4096]) and type: torch.float16

Traceback (most recent call last):
  File "/Users/ggerganov/development/github/llama.cpp/convert-pth-to-ggml.py", line 157, in <module>
    main()
  File "/Users/ggerganov/development/github/llama.cpp/convert-pth-to-ggml.py", line 151, in main
    process_and_write_variables(fout, model, ftype)
  File "/Users/ggerganov/development/github/llama.cpp/convert-pth-to-ggml.py", line 127, in process_and_write_variables
    data.tofile(fout)
AttributeError: 'Tensor' object has no attribute 'tofile'. Did you mean: 'tile'?

Any ideas?

Edit: fixed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
duplicate This issue or pull request already exists
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants