DAMO-NLP-SG / DAMO-NLP-SG/VideoLLaMA3

Training script for 7B version

Open
#88 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
1.2k
Forks
89
PR merge metrics
No merged PRs in 30d

Description

Would it be possible to release a training script for the 7B model? Preferably for the stage-1 training, but the other stages are also interesting. If this is not possible, what parameters need to be altered/added in the .sh files

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reviewing the existing .sh files and how they configure training for the available model sizes. Compare the stage-1 setup with the requested 7B model and determine which parameters would need to be altered or added. Done means either a usable 7B training script, preferably for stage 1, or documented parameter changes for the shell scripts.

Written by the indexing model from the issue text.

Assessment

Tech stack
shell
Domain
machine-learning
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.