hugpadhugpad

llava-hf / llava-v1.6-34b-hf

Vision35B2.5K95Updated Jan 27, 2025
Hugging Face

Downloads

2.5K

Likes

95

Last updated

Jan 27, 2025

License

Not available

The LLaVA-NeXT model was proposed in LLaVA-NeXT: Improved reasoning, OCR, and world knowledge by Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, Yong Jae Lee. LLaVa-NeXT (also called LLaVa-1.6) improves upon LLaVa by increasing the input image resolution…

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • llava_next
  • image-text-to-text
  • vision
  • conversational
  • en

Technical specifications

Parameters35B
Librarytransformers
Languagesen
LicenseNot available