ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

LLM: first update descriptions for ChatGLM transformers int4 example (#8646)

Browse source
This commit is contained in:
binbin Deng 2023-08-02 11:00:56 +08:00 committed by GitHub
parent 769209b7f0
commit 6fc31bb4cf
1 changed files with 11 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
python/llm/example/transformers/transformers_int4/chatglm/README.md
View file

@ -2,15 +2,21 @@
In this directory, you will find examples on how you could apply BigDL-LLM INT4 optimizations on ChatGLM models. For illustration purposes, we utilize the [THUDM/chatglm-6b](https://huggingface.co/THUDM/chatglm-6b) as a reference ChatGLM model. In this directory, you will find examples on how you could apply BigDL-LLM INT4 optimizations on ChatGLM models. For illustration purposes, we utilize the [THUDM/chatglm-6b](https://huggingface.co/THUDM/chatglm-6b) as a reference ChatGLM model.
## 0. Requirements > **Note**: If you want to download the Hugging Face *Transformers* model, please refer to [here](https://huggingface.co/docs/hub/models-downloading#using-git).
>
> BigDL-LLM optimizes the *Transformers* model in INT4 precision at runtime, so that no explicit conversion is needed.
## Requirements
To run these examples with BigDL-LLM, we have some recommended requirements for your machine, please refer to [here](../README.md#recommended-requirements) for more information. To run these examples with BigDL-LLM, we have some recommended requirements for your machine, please refer to [here](../README.md#recommended-requirements) for more information.
## Example: Predict Tokens using `generate()` API ## Example: Predict Tokens using `generate()` API
In the example [generate.py](./generate.py), we show a basic use case for a ChatGLM model to predict the next N tokens using `generate()` API, with BigDL-LLM INT4 optimizations. In the example [generate.py](./generate.py), we show a basic use case for a ChatGLM model to predict the next N tokens using `generate()` API, with BigDL-LLM INT4 optimizations.
### 1. Install ### 1. Install
We suggest using conda to manage environment: We suggest using conda to manage the Python environment. For more information about conda installation, please refer to [here](https://docs.conda.io/en/latest/miniconda.html#).
After installing conda, create a Python environment for BigDL-LLM:
```bash ```bash
conda create -n llm python=3.9 conda create -n llm python=3.9 # recommend to use Python 3.9
conda activate llm conda activate llm
pip install bigdl-llm[all] # install bigdl-llm with 'all' option pip install bigdl-llm[all] # install bigdl-llm with 'all' option
@ -26,6 +32,8 @@ Arguments info:
- `--prompt PROMPT`: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be `'AI是什么？'`. - `--prompt PROMPT`: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be `'AI是什么？'`.
- `--n-predict N_PREDICT`: argument defining the max number of tokens to predict. It is default to be `32`. - `--n-predict N_PREDICT`: argument defining the max number of tokens to predict. It is default to be `32`.
The expected output can be found in [Sample Output](#23-sample-output) section.
> **Note**: When loading the model in 4-bit, BigDL-LLM converts linear layers in the model into INT4 format. In theory, a *X*B model saved in 16-bit will requires approximately 2*X* GB of memory for loading, and ~0.5*X* GB memory for further inference. > **Note**: When loading the model in 4-bit, BigDL-LLM converts linear layers in the model into INT4 format. In theory, a *X*B model saved in 16-bit will requires approximately 2*X* GB of memory for loading, and ~0.5*X* GB memory for further inference.
> >
> Please select the appropriate size of the ChatGLM model based on the capabilities of your machine. > Please select the appropriate size of the ChatGLM model based on the capabilities of your machine.