DataLearner logoDataLearnerAI
Latest AI Insights
Model Leaderboards
Benchmarks
Model Directory
Model Comparison
Resource Center
Tools
LanguageEnglish
DataLearner logoDataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

Products

  • Leaderboards
  • Model comparison
  • Datasets

Resources

  • Tutorials
  • Editorial
  • Tool directory

Company

  • About
  • Privacy policy
  • Data methodology
  • Contact

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

Privacy policyTerms of service
Page navigation
目录
Model catalogVicuna 7B
VI

Vicuna 7B

基础大模型

Vicuna 7B

Release date: 2023-04-07更新于: 2023-08-03 14:11:49.431870
Live demoGitHubHugging FaceCompare
Parameters
7B
Context length
2K
Chinese support
Not supported
Reasoning ability

Vicuna 7B is an AI model published by LM-SYS, released on 2023-04-07, for 基础大模型, with 70.0B parameters, and 2K tokens context length, requiring about 13.5GB storage, under the 开源不可商用 license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Vicuna 7B

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
2K tokens
Max output length
No data
Model type
基础大模型
Release date
2023-04-07
Model file size
13.5GB
MoE architecture
No
Total params / Active params
7B / N/A
Knowledge cutoff
No data
Vicuna 7B

Open source & experience

Code license
Apache 2.0
Weights license
开源不可商用- 不可以商用
GitHub repo
https://github.com/lm-sys/FastChat
Hugging Face
https://huggingface.co/lmsys/vicuna-7b-delta-v0
Live demo
No live demo
Vicuna 7B

Official resources

Paper
Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality
DataLearnerAI blog
No blog post yet
Vicuna 7B

API details

API speed
No data
No public API pricing yet.
Vicuna 7B

Benchmark Results

No benchmark data to show.
Vicuna 7B

Publisher

LM-SYS
LM-SYS
View publisher details
Vicuna 7B

Model Overview

--------------2023年8月3日更新--------------------

Vicuna发布1.5版本更新的权重模型,效果更好:   https://huggingface.co/lmsys/vicuna-7b-v1.5 


Vicuna-7B是一个70亿规模的聊天机器人模型,基于MetaAI的LLaMA模型微调得到。

也是Vicuna家族的第2个成员,第一个是130亿参数规模的模型。


Vicuna-7B可以运行在MacBook电脑上,使用M1芯片。


Vicuna-7B模型是基于MetaAI开源的LLaMA模型微调得到,由于LLaMA模型原有协议的限制,本模型也无法商用,即使非商用使用也需要先申请LLaMA的预训练结果。


目前,Vicuna-7B的官方模型有2个版本,分别是delta-v0和delta-v1.1。前者发布于4月7日。4月12日,官方再次更新,发布1.1版本。


权重v1.1的主要更新有2个:

  • 重构标记化和分隔符。在Vicuna v1.1中,分隔符已从“###”更改为EOS令牌“</s>”。此更改使确定生成停止条件变得更加容易,并能够更好地与其他库兼容。
  • 修复有监督的微调损失计算,以获得更好的模型质量。

Foundation model

LLaMA
LLaMA
View details

DataLearner 官方微信

欢迎关注 DataLearner 官方微信,获得最新 AI 技术推送

DataLearner 官方微信二维码