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

StableVicuna-13B

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

2023-04-28

Model file size

26GB

MoE architecture

Total params / Active params

130.0B / N/A

Knowledge cutoff

No data

StableVicuna-13B

Open source & experience

Code license

No data

Weights license

No data

GitHub repo

https://github.com/Stability-AI/StableLM

Hugging Face

https://huggingface.co/spaces/CarperAI/StableVicuna

Live demo

No live demo

StableVicuna-13B

Official resources

Paper

Stability AI releases StableVicuna, the AI World’s First Open Source RLHF LLM Chatbot

DataLearnerAI blog

No blog post yet

StableVicuna-13B

API details

API speed

No data

No public API pricing yet.

StableVicuna-13B

Benchmark Results

No benchmark data to show.

StableVicuna-13B

Publisher

Stability AI

View publisher details

StableVicuna-13B

Model Overview

这是第一个通过强化学习从人类反馈中训练的大规模开源聊天机器人。StableVicuna是Vicuna v0 13b的进一步指令微调和RLHF训练版本，它是一个指令微调的LLaMA 13b模型。

StableVicuna由StabilityAI发布，完全开源。

Foundation model

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