InternLM / InternLM/xtuner

convert_xtuner_weights_to_llava.py and convert_xtuner_weights_to_hf.py can support llava-next model?

Open
#642 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
5.2k
Forks
448
Avg merge
3d 15h
Merged PRs (30d)
26

Description

i has use https://github.com/hhaAndroid/xtuner/tree/refactor_llava train llava_1.6_phi3_8B model .

but ,it cannot convert to office llava model use convert_xtuner_weights_to_llava.py

can you help me ?

#641
@LZHgrla @hhaAndroid

help me ? thanks

Contributor guide

Open the contributing guide

Research direction

Start by reading convert_xtuner_weights_to_llava.py and convert_xtuner_weights_to_hf.py, then review the referenced issue #641 and the llava_1.6_phi3_8B training setup. Reproduce the conversion failure with the reported weights and determine the expected official LLaVA output; done means both scripts support the llava-next model conversion.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, tooling
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.