hugohrban / ProGen2-finetuning

Finetuning ProGen2 protein language model for generation of protein sequences from selected protein families.
BSD 3-Clause "New" or "Revised" License
24 stars 2 forks source link

I cant use sample.py #2

Open chenwy804 opened 4 weeks ago

chenwy804 commented 4 weeks ago

Thank you very much for creating this software, but I am currently encountering some issues while using it. After I made some adjustments to the model and automatically saved it to the checkpoints \ hugohrban \ progen2 small finetuned \ e5 path, I am unable to use it

python sample.py \
--model=checkpoints\hugohrban\progen2-small-finetuned\e5 \
--device=cuda \
--batch_size=8 \
--iters=1 `\`
--max_length=512 \
--t=1.0 \
--k=10 \
--prompt="<|pf18828|>1MEVVIVTGMSGAGK"

To continue calling it, he will report an error huggingface_hub.errors.HFValidationError: Repo itid must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'checkpoints\hugohrban\progen2-small-finetuned\e5'. I am using this program in a Windows environment If I use an absolute path model in Linux, such as python /home/chen/data/LLM/ProGen2_finetuning-main/src/sample.py --model /home/chen/data/LLM/ProGen2_finetuning-main/src/checkpoints/hugohrban/progen2-small-finetuned/e5/ It will report an error huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/home/chen/data/LLM/ProGen2_finetuning-main/src/checkpoints/hugohrban/progen2-small-finetuned/e5/'. Userepo_typeargument if needed I am a beginner in this field, so although I have researched some information and asked relevant people, I am still unable to solve the problem. If you can provide an answer, I would be very grateful!Thank you