linkedin / linkedin/Liger-Kernel

Support the new Solar architecture

Open
#537 2 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement feature huggingface
Dominant language
Python
Stars
6.6k
Forks
603
Avg merge
1d 20h
Merged PRs (30d)
47

Description

### 🚀 The feature, motivation and pitch

This model from Upstage is extremely strong for models that fit on a single GPU for training and inference! https://huggingface.co/upstage/solar-pro-preview-instruct. However, it does use a custom architecture `solar` which is based on Llama/Mistral but modifies the forward pass to add long range residual connections. It would be awesome to support this architecture natively out of the box!

### Alternatives

_No response_

### Additional context

Thank you so much for this awesome project :)

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the existing Llama/Mistral architecture support and the linked Solar model description. Identify where Solar's custom long-range residual forward pass must be integrated; done means the Solar architecture works natively for training and inference.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.