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

Is "Convert HF checkpoint" part necessary for fintuning on custom dataset?

Open
#36 1 comment 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

once I do "Step 2: (Optional) Convert HF checkpoint", I still need to load "DAMO-NLP-SG/SigLIP-NaViT" from huggingface to get "preprocessor_config.json" and other files. In this situation, would the all parts of model be intialized with the weights correctly?

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.