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 catalogINT8 GPT-J 6B
IN

INT8 GPT-J 6B

基础大模型

INT8 GPT-J 6B

Release date: 2023-03-16更新于: 2023-03-18 16:34:53.831492
Live demoGitHubHugging FaceCompare
Parameters
60.0亿
Context length
2K
Chinese support
Not supported
Reasoning ability

INT8 GPT-J 6B is an AI model published by BigScience, released on 2023-03-16, for 基础大模型, with 60.0B parameters, and 2K tokens context length, requiring about 6 storage.

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

INT8 GPT-J 6B

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
2023-03-16
Model file size
6
MoE architecture
No
Total params / Active params
60.0B / N/A
Knowledge cutoff
No data
INT8 GPT-J 6B

Open source & experience

Code license
No data
Weights license
No data
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
No live demo
INT8 GPT-J 6B

Official resources

Paper
No paper available
DataLearnerAI blog
No blog post yet
INT8 GPT-J 6B

API details

API speed
No data
No public API pricing yet.
INT8 GPT-J 6B

Benchmark Results

No benchmark data to show.
INT8 GPT-J 6B

Publisher

BigScience
BigScience
View publisher details
INT8 GPT-J 6B

Model Overview

INT8 GPT-J 6B是GPT-J 6B的INT8量化版本,由Intel提供。


这个int8 ONNX模型是通过神经压缩器生成的,可以使用以下命令导出fp32模型:



python -m transformers.onnx --model=EleutherAI/gpt-j-6B onnx_gptj/ --framework pt --opset 13 --feature=causal-lm-with-past


测试结果如下:

INT8量化FP32版本
Lamabda数据集准确率0.79260.7954
模型大小(GB)623


可以看到,这个压缩版本使得模型从原来的23G压缩到了6G,但是准确率几乎没有下降,十分值得大家自己使用!

Foundation model

GPT-J
GPT-J
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