https://github.com/tloen/llama-int8

Quantized inference code for LLaMA models
https://github.com/tloen/llama-int8

Last synced: 3 months ago
JSON representation

Quantized inference code for LLaMA models

• Host: GitHub
• URL: https://github.com/tloen/llama-int8
• Owner: tloen
• License: gpl-3.0
• Fork: true (meta-llama/llama)
• Created: 2023-03-03T20:19:28.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-03-17T03:20:17.000Z (over 1 year ago)
• Last Synced: 2024-06-15T13:33:25.768Z (5 months ago)
• Language: Python
• Homepage:
• Size: 50.8 KB
• Stars: 1,052
• Watchers: 17
• Forks: 104
• Open Issues: 16

Awesome Lists containing this project

• awesome-ChatGPT-repositories - llama-int8 - Quantized inference code for LLaMA models (Langchain)