search

NVlabs / VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)
Apache License 2.0
970 stars 68 forks source link

Request for middle checkpoint #42

Closed jihaonew closed 12 hours ago

jihaonew commented 2 months ago

Thank you for the amazing release!

Do you plan to release the checkpoints from different stages, e.g., checkpoint before SFT? These checkpoints would be valuable for further fine-tuning.

Lyken17 commented 2 months ago

@yaolug as discussed earlier, can we also open source the middle checkpoints?

Efficient-Large-Language-Model commented 2 months ago

Yes, will do.

jihaonew commented 2 months ago

Thank you! 👀