---
title: llava-v1.6-vicuna-13b
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/llava-v1.6-vicuna-13b"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/llava-v1.6-vicuna-13b.md"
repository: AI-ModelScope/llava-v1.6-vicuna-13b
last_updated: 2024-02-01
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llava
architectures:
  - LlavaLlamaForCausalLM
parameters: 13.4B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
inference_backends:
  - "deploy_task vlm"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
downloads: 491
stars: 1
---

# llava-v1.6-vicuna-13b

> llava-v1.6-vicuna-13b - AI-ModelScope 在 ModelScope 开源的模型。Model type: LLaVA is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base…

AI-ModelScope/llava-v1.6-vicuna-13b 是 ModelScope 魔搭社区上的 13.4B 参数text-generation模型，可用 deploy_task vlm、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: AI-ModelScope/llava-v1.6-vicuna-13b
- **Tasks**: text-generation
- **Parameters**: 13.4B
- **Inference backends**: deploy_task vlm, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2
- **Downloads**: 491
- **Stars**: 1
- **Last updated**: 2024-02-01

Source: https://www.modelscope.cn/models/AI-ModelScope/llava-v1.6-vicuna-13b

---

<br>
<br>

# LLaVA Model Card

## Model details

**Model type:**
LLaVA is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data.
It is an auto-regressive language model, based on the transformer architecture.
Base LLM: [lmsys/vicuna-13b-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5)

**Model date:**
LLaVA-v1.6-Vicuna-13B was trained in December 2023.

**Paper or resources for more information:**
https://llava-vl.github.io/

## License
Llama 2 is licensed under the LLAMA 2 Community License, 
Copyright (c) Meta Platforms, Inc. All Rights Reserved.

**Where to send questions or comments about the model:**
https://github.com/haotian-liu/LLaVA/issues

## Intended use
**Primary intended uses:**
The primary use of LLaVA is research on large multimodal models and chatbots.

**Primary intended users:**
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

## Training dataset
- 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
- 158K GPT-generated multimodal instruction-following data.
- 500K academic-task-oriented VQA data mixture.
- 50K GPT-4V data mixture.
- 40K ShareGPT data.

## Evaluation dataset
A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.