hiyouga / hiyouga/FastEdit

LLaMA-2-7b-chat Editing failed

Open
#18 0 comments 0 reactions 0 assignees View on GitHub
pending
Dominant language
Python
Stars
1.4k
Forks
103
PR merge metrics
No merged PRs in 30d

Description

```bash
CUDA_VISIBLE_DEVICES=7 python -m fastedit.editor \
--data data/example.json \
--model /path/to/Llama-2-7b-chat-hf \
--config llama-7b \
--template default

RuntimeError: probability tensor contains either `inf`, `nan` or element < 0
```

It will be `inf` in generate processing. This method is only use for pretrained model like `Llama-2-7b-hf`?

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reproducing the command through the fastedit.editor entry point with data/example.json, the llama-7b config, and the default template. Compare the failure with the Llama-2-7b-chat-hf model against the pretrained model mentioned in the report and trace where generation produces invalid probabilities. Done means the supported-model behavior is fixed or the chat-model limitation is clearly documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.