Any examples using transformers for custom model plugins?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 12.5k
- Forks
- 998
- Avg merge
- 3d 13h
- Merged PRs (30d)
- 10
Description
I'm working on integrating AutoGPTQ (https://github.com/PanQiWei/AutoGPTQ/) as a plugin, and running into random errors or unexpected behavior along the way. Took a look at mpt and gpt4all, but both are too different from transformers to give me a good idea on this more general purpose plugin for loading any gptq'd LLM.
Even just some simple code snippets on using transformers generate function in a plugin would be helpful.
Thanks!
Contributor guide
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 by reviewing the existing mpt and gpt4all plugin examples, then compare them with the transformers generate function mentioned in the issue. Done would be clear example snippets showing how a custom plugin can load a GPTQ model through this general-purpose path.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100