search

Efficient-Large-Model / 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
878 stars 55 forks source link

Request for middle checkpoint #42

Open jihaonew opened 1 month ago

jihaonew commented 1 month 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 1 month ago

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

Efficient-Large-Language-Model commented 1 month ago

Yes, will do.

jihaonew commented 1 month ago

Thank you! 👀