metadata
license: llama2
pipeline_tag: text-generation
Tags:
- cortex.cpp
- multimodal
- vicuna
- vision-language
Overview
LLaVA (Large Language and Vision Assistant) is an open-source chatbot trained to handle multimodal instruction-following tasks. It is a fine-tuned Vicuna-7B model, designed to process both text and image inputs. This auto-regressive language model leverages the transformer architecture to improve interactions in vision-language tasks, making it useful for research in computer vision, natural language processing, machine learning, and artificial intelligence.
LLaVA-v1.6-Vicuna-7B is the latest iteration, trained in December 2023, and optimized for improved instruction-following performance in multimodal settings.
Variants
| No | Variant | Cortex CLI command |
|---|---|---|
| 1 | llava-v1.6-vicuna-7b-f16 | cortex run llava-v1.6:gguf-f16 |
| 2 | llava-v1.6-vicuna-7b-q4_km | cortex run llava-v1.6:gguf-q4-km |
Use it with Jan (UI)
- Install Jan using Quickstart
- Use in Jan model Hub:
cortexso/llava-v1.6
Use it with Cortex (CLI)
- Install Cortex using Quickstart
- Run the model with command:
cortex run llava-v1.6
Credits
- Author: LLaVA Research Team
- Converter: Homebrew
- Original License: LLAMA 2 Community License
- Papers: LLaVA-v1.6: Enhancing Large Multimodal Models