DAMO-NLP-SG / DAMO-NLP-SG/VideoLLaMA3
Is "Convert HF checkpoint" part necessary for fintuning on custom dataset?
Open
- 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.