ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
ipex-llm/python/llm/portable-zip
History
Wang, Jian4 9df70d95eb
Refactor bigdl.llm to ipex_llm (#24) 
* Rename bigdl/llm to ipex_llm

* rm python/llm/src/bigdl

* from bigdl.llm to from ipex_llm
2024-03-22 15:41:21 +08:00
..
.gitignore LLM: add ui for portable-zip (#9262) 2023-11-01 15:36:59 +08:00
chat-ui.bat Refactor bigdl.llm to ipex_llm (#24) 2024-03-22 15:41:21 +08:00
chat.bat LLM: adjust portable zip content (#9054) 2023-10-09 10:51:19 +08:00
chat.py Refactor bigdl.llm to ipex_llm (#24) 2024-03-22 15:41:21 +08:00
kv_cache.py LLM: improve response speed in multi-turn chat (#9299) 2023-11-01 10:30:44 +08:00
README-ui.md LLM: add ui for portable-zip (#9262) 2023-11-01 15:36:59 +08:00
README.md LLM: fix portable zip README image link (#9201) 2023-10-17 16:38:22 +08:00
setup.bat LLM: add ui for portable-zip (#9262) 2023-11-01 15:36:59 +08:00
setup.md LLM: add ui for portable-zip (#9262) 2023-11-01 15:36:59 +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.