alibaba / alibaba/ROLL

LVLM Lora相关内容有计划更新吗

Open
#420 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
3.4k
Forks
312
Avg merge
1h 2m
Merged PRs (30d)
2

Description

新版代码对比了一下rlvr_vlm_pipeline.py和rlvr_pipeline.py,好像Lora相关的内容不是很完全,比如self.use_ref_model这种flag控制等

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by comparing rlvr_vlm_pipeline.py with rlvr_pipeline.py, focusing on the LoRA-related paths and the self.use_ref_model flag. Document which behavior is missing in the LVLM pipeline and define done as bringing the intended LoRA controls into parity with the reference pipeline.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.