CoolFace
Modelpublic

ali-vosoughi/oscar-llava-v1.5-13b-projector

sourceHugging Faceotherupdated 6mo agoView on Hugging Face
0likes15downloads
Model Card

OSCaR LLaVA v1.5 13B Projector

This repository contains the projector artifact staged for the OSCaR public release.

Artifact Type

  • —Local staging directory: llava-v1.5-13b-pretrain-projector
  • —Public repo id: ali-vosoughi/oscar-llava-v1.5-13b-projector
  • —Training data condition: projector pretraining assets used before OSCaR LoRA fine-tuning

Files

  • —config.json
  • —mm_projector.bin

Loading

This is a projector-only release. It is intended for the pretraining and fine-tuning workflow documented in the OSCaR code repository.

Example:

bash
bash scripts/train/pretrain_v1_5_13b_projector.sh

Training Configuration

  • —LLaVA v1.5 stack
  • —CLIP ViT-L/336 vision tower
  • —LoRA rank 128
  • —LoRA alpha 256
  • —learning rate 2e-4
  • —1 epoch
  • —max sequence length 2048

Related Resources

  • —Code: https://github.com/nguyennm1024/OSCaR
  • —Dataset: https://huggingface.co/datasets/ali-vosoughi/oscar-dataset
  • —Paper: https://arxiv.org/abs/2402.17128