Add GPU example for GLM-4 (#11267)
* Add GPU example for GLM-4 * Update streamchat.py * Fix pretrianed arguments Fix pretrained arguments in generate and streamchat.py * Update Readme Update install tiktoken required for GLM-4 * Update comments in generate.py
This commit is contained in:
Zijie Li
GitHub
parent
0d9cc9c106
commit
40fc8704c4
5 changed files with 636 additions and 0 deletions
|
|
@ -0,0 +1,265 @@
|
|||
# GLM-4
|
||||
In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on GLM-4 models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [THUDM/glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat) as a reference InternLM model.
|
||||
|
||||
## 0. Requirements
|
||||
To run these examples with IPEX-LLM on Intel GPUs, we have some recommended requirements for your machine, please refer to [here](../../../README.md#requirements) for more information.
|
||||
|
||||
## Example 1: Predict Tokens using `generate()` API
|
||||
In the example [generate.py](./generate.py), we show a basic use case for a GLM-4 model to predict the next N tokens using `generate()` API, with IPEX-LLM INT4 optimizations on Intel GPUs.
|
||||
### 1. Install
|
||||
#### 1.1 Installation on Linux
|
||||
We suggest using conda to manage environment:
|
||||
```bash
|
||||
conda create -n llm python=3.11
|
||||
conda activate llm
|
||||
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
|
||||
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
||||
|
||||
# install tiktoken required for GLM-4
|
||||
pip install tiktoken
|
||||
```
|
||||
|
||||
#### 1.2 Installation on Windows
|
||||
We suggest using conda to manage environment:
|
||||
```bash
|
||||
conda create -n llm python=3.11 libuv
|
||||
conda activate llm
|
||||
|
||||
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
|
||||
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
||||
|
||||
# install tiktoken required for GLM-4
|
||||
pip install tiktoken
|
||||
```
|
||||
|
||||
### 2. Configures OneAPI environment variables for Linux
|
||||
|
||||
> [!NOTE]
|
||||
> Skip this step if you are running on Windows.
|
||||
|
||||
This is a required step on Linux for APT or offline installed oneAPI. Skip this step for PIP-installed oneAPI.
|
||||
|
||||
```bash
|
||||
source /opt/intel/oneapi/setvars.sh
|
||||
```
|
||||
|
||||
### 3. Runtime Configurations
|
||||
For optimal performance, it is recommended to set several environment variables. Please check out the suggestions based on your device.
|
||||
#### 3.1 Configurations for Linux
|
||||
<details>
|
||||
|
||||
<summary>For Intel Arc™ A-Series Graphics and Intel Data Center GPU Flex Series</summary>
|
||||
|
||||
```bash
|
||||
export USE_XETLA=OFF
|
||||
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
|
||||
export SYCL_CACHE_PERSISTENT=1
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
|
||||
<summary>For Intel Data Center GPU Max Series</summary>
|
||||
|
||||
```bash
|
||||
export LD_PRELOAD=${LD_PRELOAD}:${CONDA_PREFIX}/lib/libtcmalloc.so
|
||||
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
|
||||
export SYCL_CACHE_PERSISTENT=1
|
||||
export ENABLE_SDP_FUSION=1
|
||||
```
|
||||
> Note: Please note that `libtcmalloc.so` can be installed by `conda install -c conda-forge -y gperftools=2.10`.
|
||||
</details>
|
||||
|
||||
<details>
|
||||
|
||||
<summary>For Intel iGPU</summary>
|
||||
|
||||
```bash
|
||||
export SYCL_CACHE_PERSISTENT=1
|
||||
export BIGDL_LLM_XMX_DISABLED=1
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
#### 3.2 Configurations for Windows
|
||||
<details>
|
||||
|
||||
<summary>For Intel iGPU</summary>
|
||||
|
||||
```cmd
|
||||
set SYCL_CACHE_PERSISTENT=1
|
||||
set BIGDL_LLM_XMX_DISABLED=1
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
|
||||
<summary>For Intel Arc™ A-Series Graphics</summary>
|
||||
|
||||
```cmd
|
||||
set SYCL_CACHE_PERSISTENT=1
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
> [!NOTE]
|
||||
> For the first time that each model runs on Intel iGPU/Intel Arc™ A300-Series or Pro A60, it may take several minutes to compile.
|
||||
### 4. Running examples
|
||||
|
||||
```
|
||||
python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT
|
||||
```
|
||||
|
||||
Arguments info:
|
||||
- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the GLM-4 model (e.g. `THUDM/glm-4-9b-chat`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'THUDM/glm-4-9b-chat'`.
|
||||
- `--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`.
|
||||
|
||||
#### Sample Output
|
||||
##### [THUDM/glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat)
|
||||
```log
|
||||
Inference time: xxxx s
|
||||
-------------------- Prompt --------------------
|
||||
<|user|>
|
||||
AI是什么？
|
||||
<|assistant|>
|
||||
-------------------- Output --------------------
|
||||
|
||||
AI是什么？
|
||||
|
||||
AI，即人工智能（Artificial Intelligence），是指由人创造出来的，能够模拟、延伸和扩展人的智能的计算机系统或机器。人工智能的目标
|
||||
```
|
||||
|
||||
```log
|
||||
Inference time: xxxx s
|
||||
-------------------- Prompt --------------------
|
||||
<|user|>
|
||||
What is AI?
|
||||
<|assistant|>
|
||||
-------------------- Output --------------------
|
||||
|
||||
What is AI?
|
||||
|
||||
Artificial Intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. The term "art
|
||||
```
|
||||
|
||||
## Example 2: Stream Chat using `stream_chat()` API
|
||||
In the example [streamchat.py](./streamchat.py), we show a basic use case for a GLM-4 model to stream chat, with IPEX-LLM INT4 optimizations.
|
||||
### 1. Install
|
||||
#### 1.1 Installation on Linux
|
||||
We suggest using conda to manage environment:
|
||||
```bash
|
||||
conda create -n llm python=3.11
|
||||
conda activate llm
|
||||
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
|
||||
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
||||
|
||||
# install tiktoken required for GLM-4
|
||||
pip install tiktoken
|
||||
```
|
||||
|
||||
#### 1.2 Installation on Windows
|
||||
We suggest using conda to manage environment:
|
||||
```bash
|
||||
conda create -n llm python=3.11 libuv
|
||||
conda activate llm
|
||||
|
||||
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
|
||||
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
||||
|
||||
# install tiktoken required for GLM-4
|
||||
pip install tiktoken
|
||||
```
|
||||
|
||||
### 2. Configures OneAPI environment variables for Linux
|
||||
|
||||
> [!NOTE]
|
||||
> Skip this step if you are running on Windows.
|
||||
|
||||
This is a required step on Linux for APT or offline installed oneAPI. Skip this step for PIP-installed oneAPI.
|
||||
|
||||
```bash
|
||||
source /opt/intel/oneapi/setvars.sh
|
||||
```
|
||||
|
||||
### 3. Runtime Configurations
|
||||
For optimal performance, it is recommended to set several environment variables. Please check out the suggestions based on your device.
|
||||
#### 3.1 Configurations for Linux
|
||||
<details>
|
||||
|
||||
<summary>For Intel Arc™ A-Series Graphics and Intel Data Center GPU Flex Series</summary>
|
||||
|
||||
```bash
|
||||
export USE_XETLA=OFF
|
||||
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
|
||||
export SYCL_CACHE_PERSISTENT=1
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
|
||||
<summary>For Intel Data Center GPU Max Series</summary>
|
||||
|
||||
```bash
|
||||
export LD_PRELOAD=${LD_PRELOAD}:${CONDA_PREFIX}/lib/libtcmalloc.so
|
||||
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
|
||||
export SYCL_CACHE_PERSISTENT=1
|
||||
export ENABLE_SDP_FUSION=1
|
||||
```
|
||||
> Note: Please note that `libtcmalloc.so` can be installed by `conda install -c conda-forge -y gperftools=2.10`.
|
||||
</details>
|
||||
|
||||
<details>
|
||||
|
||||
<summary>For Intel iGPU</summary>
|
||||
|
||||
```bash
|
||||
export SYCL_CACHE_PERSISTENT=1
|
||||
export BIGDL_LLM_XMX_DISABLED=1
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
#### 3.2 Configurations for Windows
|
||||
<details>
|
||||
|
||||
<summary>For Intel iGPU</summary>
|
||||
|
||||
```cmd
|
||||
set SYCL_CACHE_PERSISTENT=1
|
||||
set BIGDL_LLM_XMX_DISABLED=1
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
|
||||
<summary>For Intel Arc™ A-Series Graphics</summary>
|
||||
|
||||
```cmd
|
||||
set SYCL_CACHE_PERSISTENT=1
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
> [!NOTE]
|
||||
> For the first time that each model runs on Intel iGPU/Intel Arc™ A300-Series or Pro A60, it may take several minutes to compile.
|
||||
### 4. Running examples
|
||||
|
||||
**Stream Chat using `stream_chat()` API**:
|
||||
```
|
||||
python ./streamchat.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --question QUESTION
|
||||
```
|
||||
|
||||
**Chat using `chat()` API**:
|
||||
```
|
||||
python ./streamchat.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --question QUESTION --disable-stream
|
||||
```
|
||||
|
||||
Arguments info:
|
||||
- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the GLM-4 model to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'THUDM/glm-4-9b-chat'`.
|
||||
- `--question QUESTION`: argument defining the question to ask. It is default to be `"AI是什么？"`.
|
||||
- `--disable-stream`: argument defining whether to stream chat. If include `--disable-stream` when running the script, the stream chat is disabled and `chat()` API is used.
|
||||
|
|
@ -0,0 +1,78 @@
|
|||
#
|
||||
# Copyright 2016 The BigDL Authors.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
#
|
||||
|
||||
import torch
|
||||
import time
|
||||
import argparse
|
||||
import numpy as np
|
||||
|
||||
from ipex_llm.transformers import AutoModel
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
# you could tune the prompt based on your own model,
|
||||
# here the prompt tuning refers to https://huggingface.co/THUDM/glm-4-9b-chat/blob/main/tokenization_chatglm.py
|
||||
GLM4_PROMPT_FORMAT = "<|user|>\n{prompt}\n<|assistant|>"
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for GLM-4 model')
|
||||
parser.add_argument('--repo-id-or-model-path', type=str, default="THUDM/glm-4-9b-chat",
|
||||
help='The huggingface repo id for the GLM-4 model to be downloaded'
|
||||
', or the path to the huggingface checkpoint folder')
|
||||
parser.add_argument('--prompt', type=str, default="AI是什么？",
|
||||
help='Prompt to infer')
|
||||
parser.add_argument('--n-predict', type=int, default=32,
|
||||
help='Max tokens to predict')
|
||||
|
||||
args = parser.parse_args()
|
||||
model_path = args.repo_id_or_model_path
|
||||
|
||||
# Load model in 4 bit,
|
||||
# which convert the relevant layers in the model into INT4 format
|
||||
# When running LLMs on Intel iGPUs for Windows users, we recommend setting `cpu_embedding=True` in the from_pretrained function.
|
||||
# This will allow the memory-intensive embedding layer to utilize the CPU instead of iGPU.
|
||||
model = AutoModel.from_pretrained(model_path,
|
||||
load_in_4bit=True,
|
||||
optimize_model=True,
|
||||
trust_remote_code=True,
|
||||
use_cache=True)
|
||||
model = model.to("xpu")
|
||||
|
||||
# Load tokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path,
|
||||
trust_remote_code=True)
|
||||
|
||||
# Generate predicted tokens
|
||||
with torch.inference_mode():
|
||||
prompt = GLM4_PROMPT_FORMAT.format(prompt=args.prompt)
|
||||
input_ids = tokenizer.encode(prompt, return_tensors="pt").to('xpu')
|
||||
|
||||
# ipex_llm model needs a warmup, then inference time can be accurate
|
||||
output = model.generate(input_ids,
|
||||
max_new_tokens=args.n_predict)
|
||||
|
||||
st = time.time()
|
||||
|
||||
output = model.generate(input_ids,
|
||||
max_new_tokens=args.n_predict)
|
||||
|
||||
torch.xpu.synchronize()
|
||||
end = time.time()
|
||||
output_str = tokenizer.decode(output[0], skip_special_tokens=True)
|
||||
print(f'Inference time: {end-st} s')
|
||||
print('-'*20, 'Prompt', '-'*20)
|
||||
print(prompt)
|
||||
print('-'*20, 'Output', '-'*20)
|
||||
print(output_str)
|
||||
|
|
@ -0,0 +1,69 @@
|
|||
#
|
||||
# Copyright 2016 The BigDL Authors.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
#
|
||||
|
||||
import torch
|
||||
import time
|
||||
import argparse
|
||||
import numpy as np
|
||||
|
||||
from ipex_llm.transformers import AutoModel
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser(description='Stream Chat for GLM-4 model')
|
||||
parser.add_argument('--repo-id-or-model-path', type=str, default="THUDM/glm-4-9b-chat",
|
||||
help='The huggingface repo id for the GLM-4 model to be downloaded'
|
||||
', or the path to the huggingface checkpoint folder')
|
||||
parser.add_argument('--question', type=str, default="晚上睡不着应该怎么办",
|
||||
help='Qustion you want to ask')
|
||||
parser.add_argument('--disable-stream', action="store_true",
|
||||
help='Disable stream chat')
|
||||
|
||||
args = parser.parse_args()
|
||||
model_path = args.repo_id_or_model_path
|
||||
disable_stream = args.disable_stream
|
||||
|
||||
# Load model in 4 bit,
|
||||
# which convert the relevant layers in the model into INT4 format
|
||||
# When running LLMs on Intel iGPUs for Windows users, we recommend setting `cpu_embedding=True` in the from_pretrained function.
|
||||
# This will allow the memory-intensive embedding layer to utilize the CPU instead of iGPU.
|
||||
model = AutoModel.from_pretrained(model_path,
|
||||
trust_remote_code=True,
|
||||
load_in_4bit=True,
|
||||
optimize_model=True,
|
||||
use_cache=True,
|
||||
cpu_embedding=True)
|
||||
|
||||
model = model.to('xpu')
|
||||
|
||||
# Load tokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path,
|
||||
trust_remote_code=True)
|
||||
|
||||
with torch.inference_mode():
|
||||
if disable_stream:
|
||||
# Chat
|
||||
response, history = model.chat(tokenizer, args.question, history=[])
|
||||
print('-'*20, 'Chat Output', '-'*20)
|
||||
print(response)
|
||||
else:
|
||||
# Stream chat
|
||||
response_ = ""
|
||||
print('-'*20, 'Stream Chat Output', '-'*20)
|
||||
for response, history in model.stream_chat(tokenizer, args.question, history=[]):
|
||||
print(response.replace(response_, ""), end="")
|
||||
response_ = response
|
||||
147
python/llm/example/GPU/PyTorch-Models/Model/glm4/README.md
Normal file
147
python/llm/example/GPU/PyTorch-Models/Model/glm4/README.md
Normal file
|
|
@ -0,0 +1,147 @@
|
|||
# GLM-4
|
||||
In this directory, you will find examples on how you could use IPEX-LLM `optimize_model` API to accelerate GLM-4 models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [THUDM/glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat) as a reference GLM-4 model.
|
||||
|
||||
## 0. Requirements
|
||||
To run these examples with IPEX-LLM on Intel GPUs, we have some recommended requirements for your machine, please refer to [here](../../../README.md#requirements) for more information.
|
||||
|
||||
## Example: Predict Tokens using `generate()` API
|
||||
In the example [generate.py](./generate.py), we show a basic use case for a GLM-4 model to predict the next N tokens using `generate()` API, with IPEX-LLM INT4 optimizations on Intel GPUs.
|
||||
### 1. Install
|
||||
#### 1.1 Installation on Linux
|
||||
We suggest using conda to manage environment:
|
||||
```bash
|
||||
conda create -n llm python=3.11
|
||||
conda activate llm
|
||||
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
|
||||
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
||||
|
||||
# install tiktoken required for GLM-4
|
||||
pip install tiktoken
|
||||
```
|
||||
|
||||
#### 1.2 Installation on Windows
|
||||
We suggest using conda to manage environment:
|
||||
```bash
|
||||
conda create -n llm python=3.11 libuv
|
||||
conda activate llm
|
||||
|
||||
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
|
||||
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
||||
|
||||
# install tiktoken required for GLM-4
|
||||
pip install tiktoken
|
||||
```
|
||||
|
||||
### 2. Configures OneAPI environment variables for Linux
|
||||
|
||||
> [!NOTE]
|
||||
> Skip this step if you are running on Windows.
|
||||
|
||||
This is a required step on Linux for APT or offline installed oneAPI. Skip this step for PIP-installed oneAPI.
|
||||
|
||||
```bash
|
||||
source /opt/intel/oneapi/setvars.sh
|
||||
```
|
||||
|
||||
### 3. Runtime Configurations
|
||||
For optimal performance, it is recommended to set several environment variables. Please check out the suggestions based on your device.
|
||||
#### 3.1 Configurations for Linux
|
||||
<details>
|
||||
|
||||
<summary>For Intel Arc™ A-Series Graphics and Intel Data Center GPU Flex Series</summary>
|
||||
|
||||
```bash
|
||||
export USE_XETLA=OFF
|
||||
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
|
||||
export SYCL_CACHE_PERSISTENT=1
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
|
||||
<summary>For Intel Data Center GPU Max Series</summary>
|
||||
|
||||
```bash
|
||||
export LD_PRELOAD=${LD_PRELOAD}:${CONDA_PREFIX}/lib/libtcmalloc.so
|
||||
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
|
||||
export SYCL_CACHE_PERSISTENT=1
|
||||
export ENABLE_SDP_FUSION=1
|
||||
```
|
||||
> Note: Please note that `libtcmalloc.so` can be installed by `conda install -c conda-forge -y gperftools=2.10`.
|
||||
</details>
|
||||
|
||||
<details>
|
||||
|
||||
<summary>For Intel iGPU</summary>
|
||||
|
||||
```bash
|
||||
export SYCL_CACHE_PERSISTENT=1
|
||||
export BIGDL_LLM_XMX_DISABLED=1
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
#### 3.2 Configurations for Windows
|
||||
<details>
|
||||
|
||||
<summary>For Intel iGPU</summary>
|
||||
|
||||
```cmd
|
||||
set SYCL_CACHE_PERSISTENT=1
|
||||
set BIGDL_LLM_XMX_DISABLED=1
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
|
||||
<summary>For Intel Arc™ A-Series Graphics</summary>
|
||||
|
||||
```cmd
|
||||
set SYCL_CACHE_PERSISTENT=1
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
> [!NOTE]
|
||||
> For the first time that each model runs on Intel iGPU/Intel Arc™ A300-Series or Pro A60, it may take several minutes to compile.
|
||||
### 4. Running examples
|
||||
|
||||
```
|
||||
python ./generate.py --prompt 'What is AI?'
|
||||
```
|
||||
|
||||
Arguments info:
|
||||
- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the GLM-4 model (e.g. `THUDM/glm-4-9b-chat`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'THUDM/glm-4-9b-chat'`.
|
||||
- `--prompt PROMPT`: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be `'What is AI?'`.
|
||||
- `--n-predict N_PREDICT`: argument defining the max number of tokens to predict. It is default to be `32`.
|
||||
|
||||
#### Sample Output
|
||||
#### [THUDM/glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat)
|
||||
|
||||
```log
|
||||
Inference time: xxxx s
|
||||
-------------------- Prompt --------------------
|
||||
<|user|>
|
||||
AI是什么？
|
||||
<|assistant|>
|
||||
-------------------- Output --------------------
|
||||
|
||||
AI是什么？
|
||||
|
||||
AI，即人工智能（Artificial Intelligence），是指由人创造出来的，能够模拟、延伸和扩展人的智能的计算机系统或机器。人工智能的目标
|
||||
```
|
||||
|
||||
```log
|
||||
Inference time: xxxx s
|
||||
-------------------- Prompt --------------------
|
||||
<|user|>
|
||||
What is AI?
|
||||
<|assistant|>
|
||||
-------------------- Output --------------------
|
||||
|
||||
What is AI?
|
||||
|
||||
Artificial Intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. The term "art
|
||||
```
|
||||
77
python/llm/example/GPU/PyTorch-Models/Model/glm4/generate.py
Normal file
77
python/llm/example/GPU/PyTorch-Models/Model/glm4/generate.py
Normal file
|
|
@ -0,0 +1,77 @@
|
|||
#
|
||||
# Copyright 2016 The BigDL Authors.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
#
|
||||
|
||||
import torch
|
||||
import time
|
||||
import argparse
|
||||
|
||||
from transformers import AutoModel, AutoTokenizer
|
||||
from ipex_llm import optimize_model
|
||||
|
||||
# you could tune the prompt based on your own model,
|
||||
# here the prompt tuning refers to https://huggingface.co/THUDM/glm-4-9b-chat/blob/main/tokenization_chatglm.py
|
||||
GLM4_PROMPT_FORMAT = "<|user|>\n{prompt}\n<|assistant|>"
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for GLM-4 model')
|
||||
parser.add_argument('--repo-id-or-model-path', type=str, default="THUDM/glm-4-9b-chat",
|
||||
help='The huggingface repo id for the GLM-4 model to be downloaded'
|
||||
', or the path to the huggingface checkpoint folder')
|
||||
parser.add_argument('--prompt', type=str, default="AI是什么？",
|
||||
help='Prompt to infer')
|
||||
parser.add_argument('--n-predict', type=int, default=32,
|
||||
help='Max tokens to predict')
|
||||
|
||||
args = parser.parse_args()
|
||||
model_path = args.repo_id_or_model_path
|
||||
|
||||
# Load model
|
||||
# When running LLMs on Intel iGPUs for Windows users, we recommend setting `cpu_embedding=True` in the from_pretrained function.
|
||||
# This will allow the memory-intensive embedding layer to utilize the CPU instead of iGPU.
|
||||
model = AutoModel.from_pretrained(model_path,
|
||||
trust_remote_code=True,
|
||||
torch_dtype = 'auto',
|
||||
low_cpu_mem_usage=True,
|
||||
use_cache=True)
|
||||
|
||||
# With only one line to enable IPEX-LLM optimization on model
|
||||
model = optimize_model(model)
|
||||
model = model.to('xpu')
|
||||
|
||||
# Load tokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path,
|
||||
trust_remote_code=True)
|
||||
|
||||
# Generate predicted tokens
|
||||
with torch.inference_mode():
|
||||
prompt = GLM4_PROMPT_FORMAT.format(prompt=args.prompt)
|
||||
input_ids = tokenizer.encode(prompt, return_tensors="pt").to('xpu')
|
||||
|
||||
# ipex_llm model needs a warmup, then inference time can be accurate
|
||||
output = model.generate(input_ids,
|
||||
max_new_tokens=args.n_predict)
|
||||
|
||||
st = time.time()
|
||||
output = model.generate(input_ids,
|
||||
max_new_tokens=args.n_predict)
|
||||
torch.xpu.synchronize()
|
||||
end = time.time()
|
||||
output_str = tokenizer.decode(output[0], skip_special_tokens=True)
|
||||
print(f'Inference time: {end-st} s')
|
||||
print('-'*20, 'Prompt', '-'*20)
|
||||
print(prompt)
|
||||
print('-'*20, 'Output', '-'*20)
|
||||
print(output_str)
|
||||
Loading…
Reference in a new issue