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

Goat

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

2K tokens

Max output length

No data

Model type

聊天大模型

Release date

2023-05-23

Model file size

No data

MoE architecture

Total params / Active params

70.0B / N/A

Knowledge cutoff

No data

Goat

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- 免费商用授权

GitHub repo

https://github.com/liutiedong/goat

Hugging Face

Hugging Face link unavailable

Live demo

No live demo

Goat

Official resources

Paper

Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks

DataLearnerAI blog

No blog post yet

Goat

API details

API speed

No data

No public API pricing yet.

Goat

Benchmark Results

No benchmark data to show.

Goat

Publisher

个人

View publisher details

GOod at Arithmetic Tasks

Model Overview

Goat是一个针对数学优化的大模型，基于LLaMA模型微调。目前开源的是70亿参数规模，是Goat-7B，但是它的数学能力比GPT-4更强！

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