(Error while merging the llama hf and vicuna delta)OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory /root/autodl-tmp/Vicuna-7B/vicuna-7b-delta.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory /root/autodl-tmp/Vicuna-7B/vicuna-7b-delta.
Anyone has some idea why this is happening? Any information is appreciated.
It seems like that I can't run
python -m fastchat.model.apply_delta \
--base-model-path /root/autodl-tmp/Vicuna-7B/llama-7b \
--target-model-path /root/autodl-tmp/Vicuna-7B/vicuna-7b \
--delta-path /root/autodl-tmp/Vicuna-7B/vicuna-7b-delta
command on both my windows computer and linux server.
Thank you very much for any information.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the fastchat.model.apply_delta entry point and reproduce the supplied command using the listed base, target, and delta paths. Check whether the model directories contain one of the files named in the OSError; done means the merge command runs without this missing-model-file error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100