yorickvp / llava-v1.6-vicuna-13b

LLaVA v1.6: Large Language and Vision Assistant (Vicuna-13B)

  • Public
  • 3.3M runs
  • GitHub
  • License
Run with an API
Playground API Examples README Versions

Run time and cost

This model costs approximately $0.046 to run on Replicate, or 21 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 64 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Check out the different LLaVA’s on Replicate:

Name Version Base Size Finetunable
v1.5 - Vicuna-13B v1.5 Vicuna 13B Yes
v1.6 - Vicuna-13B v1.6 Vicuna 13B No
v1.6 - Vicuna-7B v1.6 Vicuna 7B No
v1.6 - Mistral-7B v1.6 Mistral 7B No
v1.6 - Nous-Hermes-2-34B v1.6 Nous-Hermes-2 34B No

🌋 LLaVA v1.6: Large Language and Vision Assistant

Visual instruction tuning towards large language and vision models with GPT-4 level capabilities.

[Project Page] [Demo] [Data] [Model Zoo]

Improved Baselines with Visual Instruction Tuning [Paper]
Haotian Liu, Chunyuan Li, Yuheng Li, Yong Jae Lee

Visual Instruction Tuning (NeurIPS 2023, Oral) [Paper]
Haotian Liu*, Chunyuan Li*, Qingyang Wu, Yong Jae Lee (*Equal Contribution)

LLaVA v1.6 changes

LLaVA-1.6 is out! With additional scaling to LLaVA-1.5, LLaVA-1.6-34B outperforms Gemini Pro on some benchmarks. It can now process 4x more pixels and perform more tasks/applications than before. Check out the blog post!

Summary

LLaVA represents a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding, achieving impressive chat capabilities mimicking spirits of the multimodal GPT-4 and setting a new state-of-the-art accuracy on Science QA.