simonw / simonw/llm

Support Janus-Pro-7b for vision models

Open
#758 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
12.5k
Forks
998
Avg merge
3d 13h
Merged PRs (30d)
10

Description

Simon, I'm a huge fan of your quality work and quality writing.
I recently stumbled upon llm due to MLX support.
Given the name of the package and MLX support, I see a great future in llm.

I love the DX of Ollama but user opened issues often take quite a while to get resolved.
Given this I think this would be an amazing opportunity to implement Janus for llm.

What are your thoughts and how can this be implemented along the way.

For reference:

Just announced and performing great with OCR
https://huggingface.co/deepseek-ai/Janus-Pro-7B

https://github.com/ollama/ollama/issues/8618
https://github.com/deepseek-ai/Janus/issues/9

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

The issue names no files, tests, or entry points. Start with the Janus-Pro-7B model page and the linked Ollama and Janus issues, then review the existing MLX support to assess the integration path. Done criteria are not specified and need maintainer clarification.

Written by the indexing model from the issue text.

Assessment

Tech stack
ollama, python
Domain
ai, cli
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.