Lin-Chen/ShareGPT4V
Viewer • Updated • 1.35M • 2.03k • 311
How to use xtuner/llava-llama-3-8b-v1_1-pretrain with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("visual-question-answering", model="xtuner/llava-llama-3-8b-v1_1-pretrain") # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("xtuner/llava-llama-3-8b-v1_1-pretrain", dtype="auto")llava-llama-3-8b-v1_1-pretrain is a LLaVA projector pretrained from Meta-Llama-3-8B-Instruct and CLIP-ViT-Large-patch14-336 on ShareGPT4V-PT dataset by XTuner.
The fine-tuned LLaVA model can be found on xtuner/llava-llama-3-8b-v1_1.
@misc{2023xtuner,
title={XTuner: A Toolkit for Efficiently Fine-tuning LLM},
author={XTuner Contributors},
howpublished = {\url{https://github.com/InternLM/xtuner}},
year={2023}
}