---
title: vicuna-13b-v1.5
canonical_url: "https://www.modelscope.cn/models/Xorbits/vicuna-13b-v1.5"
md_url: "https://www.modelscope.cn/models/Xorbits/vicuna-13b-v1.5.md"
repository: Xorbits/vicuna-13b-v1.5
last_updated: 2023-10-30
license: llama2
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
library_name:
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 14691
stars: 6
---

# vicuna-13b-v1.5

> vicuna-13b-v1.5 - Xorbits 在 ModelScope 开源的模型。Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.

Xorbits/vicuna-13b-v1.5 是 ModelScope 魔搭社区上的text-generation模型，采用 llama2 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: Xorbits/vicuna-13b-v1.5
- **License**: llama2
- **Tasks**: text-generation
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 14691
- **Stars**: 6
- **Last updated**: 2023-10-30

Source: https://www.modelscope.cn/models/Xorbits/vicuna-13b-v1.5

---

# Vicuna Model Card

## Model Details

Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.

- **Developed by:** [LMSYS](https://lmsys.org/)
- **Model type:** An auto-regressive language model based on the transformer architecture
- **License:** Llama 2 Community License Agreement	
- **Finetuned from model:** [Llama 2](https://arxiv.org/abs/2307.09288)

### Model Sources

- **Repository:** https://github.com/lm-sys/FastChat
- **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/
- **Paper:** https://arxiv.org/abs/2306.05685
- **Demo:** https://chat.lmsys.org/

## Uses

The primary use of Vicuna is research on large language models and chatbots.
The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.

## How to Get Started with the Model

- Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights
- APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api  

## Training Details

Vicuna v1.5 is fine-tuned from Llama 2 with supervised instruction fine-tuning.
The training data is around 125K conversations collected from ShareGPT.com.
See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).

## Evaluation

![Evaluation Results](https://github.com/lm-sys/lm-sys.github.io/blob/main/public/images/webdata/vicuna_v1.5_eval.png?raw=true)

Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf) and [leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard).

## Difference between different versions of Vicuna

See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)