Support for LFM2-VL models

Open
#2,105 1 comment 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
45/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Stale
Tech stack
python

Research direction

Look at the existing multi-modal handlers in llama-cpp-python, likely in the source directory for bindings. Understand how vision encoders (mmproj) are integrated. Check the llama-cpp documentation for LFM2-VL model specifics. Test loading a GGUF format model and adding a handler to process vision inputs.

Written by the indexing model from the issue text.

Description

Is your feature request related to a problem? Please describe.
LiquidAI provides LFM2-VL models (450M, 1.6B, 3B) as GGUF formats (Q4_0, Q8_0, F16) supported in llama-cpp.
It would be great to make them work in Python via llama-cpp-python, i.e. implement the multi-modal handler for them:
https://llama-cpp-python.readthedocs.io/en/latest/#multi-modal-models

Describe the solution you'd like
Support for LFM2-VL models (handler allowing to use mmproj of the vision encoder).

Dominant language
Python
Stars
10.7k
Forks
1.5k
Avg merge
1h 40m
Merged PRs (30d)
5

Getting set up

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.

More from abetlen/llama-cpp-python

All issues in abetlen/llama-cpp-python

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.