ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
ipex-llm/python/llm/portable-zip
History
binbin Deng 8ef8e25178 LLM: improve response speed in multi-turn chat (#9299) 
* update

* fix stop word and add chatglm2 support

* remove system prompt
2023-11-01 10:30:44 +08:00
..
.gitignore LLM: adjust portable zip content (#9054) 2023-10-09 10:51:19 +08:00
chat.bat LLM: adjust portable zip content (#9054) 2023-10-09 10:51:19 +08:00
chat.py LLM: improve response speed in multi-turn chat (#9299) 2023-11-01 10:30:44 +08:00
kv_cache.py LLM: improve response speed in multi-turn chat (#9299) 2023-11-01 10:30:44 +08:00
README.md LLM: fix portable zip README image link (#9201) 2023-10-17 16:38:22 +08:00
setup.bat LLM: adjust portable zip content (#9054) 2023-10-09 10:51:19 +08:00
setup.md LLM: adjust portable zip content (#9054) 2023-10-09 10:51:19 +08:00

README.md

BigDL-LLM Portable Zip For Windows: User Guide

Introduction

This portable zip includes everything you need to run an LLM with BigDL-LLM optimizations (except models) . Please refer to How to use section to get started.

13B model running on an Intel 11-Gen Core PC (real-time screen capture)

Verified Models

  • ChatGLM2-6b
  • Baichuan-13B-Chat
  • Baichuan2-7B-Chat
  • internlm-chat-7b-8k
  • Llama-2-7b-chat-hf

How to use

  1. Download the zip from link here.
  2. (Optional) You could also build the zip on your own. Run setup.bat and it will generate the zip file.
  3. Unzip bigdl-llm.zip.
  4. Download the model to your computer. Please ensure there is a file named config.json in the model folder, otherwise the script won't work.

  1. Go into the unzipped folder and double click chat.bat. Input the path of the model (e.g. path\to\model, note that there's no slash at the end of the path). Press Enter and wait until model finishes loading. Then enjoy chatting with the model!

  1. If you want to stop chatting, just input stop and the model will stop running.