Video-Text-to-Text
Transformers
Safetensors
English
llava
text-generation
multimodal
Eval Results (legacy)
Instructions to use lmms-lab/LLaVA-Video-7B-Qwen2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lmms-lab/LLaVA-Video-7B-Qwen2 with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("lmms-lab/LLaVA-Video-7B-Qwen2") model = AutoModelForCausalLM.from_pretrained("lmms-lab/LLaVA-Video-7B-Qwen2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Difference between 7B-DPO and 7B-Qwen2
#7
by RachelZhou - opened
Hi, I have a question regarding the differences between the following models:
- 7B
- 7B-Qwen2
- 7B-DPO
After the recent update, it seems unclear whether the 7B and 7B-DPO models still exist. Since I’m conducting studies with the 7B-DPO model, could you please clarify the differences between these models or point me to any resources that outline these differences?
Hi,the 7B-Qwen2 is our latest model
- Trained on the newest data
- Using Qwen2 as backbone
- without DPO stage