LLM: adjust portable zip content (#9054)
* LLM: adjust portable zip content * LLM: adjust portable zip README
This commit is contained in:
parent
df8df751c4
commit
65373d2a8b
9 changed files with 48 additions and 42 deletions
2
python/llm/portable-executable/.gitignore
vendored
2
python/llm/portable-executable/.gitignore
vendored
|
|
@ -1,2 +0,0 @@
|
||||||
python-embed
|
|
||||||
portable-executable.zip
|
|
||||||
|
|
@ -1,33 +0,0 @@
|
||||||
# BigDL-LLM Portable Executable For Windows: User Guide
|
|
||||||
|
|
||||||
This portable executable includes everything you need to run LLM (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)
|
|
||||||
|
|
||||||
<p align="left">
|
|
||||||
<img src=https://llm-assets.readthedocs.io/en/latest/_images/one-click-installer-screen-capture.gif width='80%' />
|
|
||||||
|
|
||||||
</p>
|
|
||||||
|
|
||||||
## 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 model to your computer. Please ensure there is a file named `config.json` in the model folder, otherwise the script won't work.
|
|
||||||
|
|
||||||

|
|
||||||
|
|
||||||
2. Run `chat.bat` in Terminal and input the path of the model (e.g. `path\to\model`, note that there's no slash at the end of the path).
|
|
||||||
|
|
||||||

|
|
||||||
|
|
||||||
3. Press Enter and wait until model finishes loading. Then enjoy chatting with the model!
|
|
||||||
4. If you want to stop chatting, just input `stop` and the model will stop running.
|
|
||||||
|
|
||||||

|
|
||||||
|
|
@ -1,5 +0,0 @@
|
||||||
# BigDL-LLM Portable Executable Setup Script For Windows
|
|
||||||
|
|
||||||
# How to use
|
|
||||||
|
|
||||||
Just simply run `setup.bat` and it will download and install all dependency and generate a zip file for user to use.
|
|
||||||
2
python/llm/portable-zip/.gitignore
vendored
Normal file
2
python/llm/portable-zip/.gitignore
vendored
Normal file
|
|
@ -0,0 +1,2 @@
|
||||||
|
python-embed
|
||||||
|
bigdl-llm.zip
|
||||||
37
python/llm/portable-zip/README.md
Normal file
37
python/llm/portable-zip/README.md
Normal file
|
|
@ -0,0 +1,37 @@
|
||||||
|
# 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](#how-to-use) section to get started.
|
||||||
|
|
||||||
|
### 13B model running on an Intel 11-Gen Core PC (real-time screen capture)
|
||||||
|
|
||||||
|
<p align="left">
|
||||||
|
<img src=https://llm-assets.readthedocs.io/en/latest/_images/one-click-installer-screen-capture.gif width='80%' />
|
||||||
|
|
||||||
|
</p>
|
||||||
|
|
||||||
|
### 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.
|
||||||
|
|
||||||
|

|
||||||
|
|
||||||
|
5. 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!
|
||||||
|
|
||||||
|

|
||||||
|
|
||||||
|
6. If you want to stop chatting, just input `stop` and the model will stop running.
|
||||||
|
|
||||||
|

|
||||||
|
|
@ -5,4 +5,6 @@
|
||||||
set PYTHONUNBUFFERED=1
|
set PYTHONUNBUFFERED=1
|
||||||
|
|
||||||
set /p modelpath="Please enter the model path: "
|
set /p modelpath="Please enter the model path: "
|
||||||
.\python-embed\python.exe .\chat.py --model-path="%modelpath%"
|
.\python-embed\python.exe .\chat.py --model-path="%modelpath%"
|
||||||
|
|
||||||
|
pause
|
||||||
|
|
@ -20,4 +20,4 @@ cd ..
|
||||||
%python-embed% -m pip install bigdl-llm[all] transformers_stream_generator tiktoken einops colorama
|
%python-embed% -m pip install bigdl-llm[all] transformers_stream_generator tiktoken einops colorama
|
||||||
|
|
||||||
:: compress the python and scripts
|
:: compress the python and scripts
|
||||||
powershell -Command "Compress-Archive -Path '.\python-embed', '.\chat.bat', '.\chat.py', '.\README.md' -DestinationPath .\portable-executable.zip"
|
powershell -Command "Compress-Archive -Path '.\python-embed', '.\chat.bat', '.\chat.py', '.\README.md' -DestinationPath .\bigdl-llm.zip"
|
||||||
5
python/llm/portable-zip/setup.md
Normal file
5
python/llm/portable-zip/setup.md
Normal file
|
|
@ -0,0 +1,5 @@
|
||||||
|
# BigDL-LLM Portable Zip Setup Script For Windows
|
||||||
|
|
||||||
|
# How to use
|
||||||
|
|
||||||
|
Just simply run `setup.bat` and it will download and install all dependency and generate `bigdl-llm.zip` for user to use.
|
||||||
Loading…
Reference in a new issue