-
Notifications
You must be signed in to change notification settings - Fork 9.4k
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
Add to huggingface #21
Comments
I don't think this is possible though as the model weights themselves are non-commercial bespoke license. |
Never hurts to ask though 😁 |
They have now added it. https://huggingface.co/docs/transformers/main/model_doc/llama, you need to provide the path to the weights though. |
Liyang90
pushed a commit
to Liyang90/llama
that referenced
this issue
Jul 20, 2023
Summary: We need to set this otherwise set_default_tensor_type in example_xla.py will set all devices to cuda:0. Test Plan: USE_CUDA=1 python example_cuda.py --tokenizer_path ../llama/spiece.model --max_seq_len 256 --max_batch_size 1 --temperature 0.8 --dim 4096 --n_heads 32 --n_layers 32 --mp True
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
No description provided.
The text was updated successfully, but these errors were encountered: