Add --modelscope in GPU examples for minicpm, minicpm3, baichuan2 (#12564)
* Add --modelscope for more models * minicpm --------- Co-authored-by: ATMxsp01 <shou.xu@intel.com>
This commit is contained in:
Xu, Shuo
GitHub
parent
3eeb02f1be
commit
47da3c999f
6 changed files with 102 additions and 28 deletions
|
|
@ -1,5 +1,5 @@
|
|||
# Baichuan
|
||||
In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on Baichuan2 models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [baichuan-inc/Baichuan2-7B-Chat](https://huggingface.co/baichuan-inc/Baichuan-7B-Chat) as a reference Baichuan model.
|
||||
In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on Baichuan2 models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [baichuan-inc/Baichuan2-7B-Chat](https://huggingface.co/baichuan-inc/Baichuan-7B-Chat) (or [baichuan-inc/Baichuan2-7B-Chat](https://www.modelscope.cn/models/[baichuan-inc/Baichuan2-7B-Chat]) for ModelScope) as a reference Baichuan 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.
|
||||
|
|
@ -16,6 +16,9 @@ conda activate llm
|
|||
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
||||
|
||||
pip install transformers_stream_generator # additional package required for Baichuan-7B-Chat to conduct generation
|
||||
|
||||
# [optional] only needed if you would like to use ModelScope as model hub
|
||||
pip install modelscope==1.11.0
|
||||
```
|
||||
|
||||
#### 1.2 Installation on Windows
|
||||
|
|
@ -28,6 +31,9 @@ conda activate llm
|
|||
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
||||
|
||||
pip install transformers_stream_generator # additional package required for Baichuan-7B-Chat to conduct generation
|
||||
|
||||
# [optional] only needed if you would like to use ModelScope as model hub
|
||||
pip install modelscope==1.11.0
|
||||
```
|
||||
|
||||
### 2. Configures OneAPI environment variables for Linux
|
||||
|
|
@ -95,14 +101,19 @@ set SYCL_CACHE_PERSISTENT=1
|
|||
> 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
|
||||
|
||||
```
|
||||
```bash
|
||||
# for Hugging Face model hub
|
||||
python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT
|
||||
|
||||
# for ModelScope model hub
|
||||
python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT --modelscope
|
||||
```
|
||||
|
||||
Arguments info:
|
||||
- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the Baichuan model (e.g `baichuan-inc/Baichuan2-7B-Chat`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'baichuan-inc/Baichuan2-7B-Chat'`.
|
||||
- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the **Hugging Face** or **ModelScope** repo id for the Baichuan model (e.g `baichuan-inc/Baichuan2-7B-Chat`) to be downloaded, or the path to the checkpoint folder. It is default to be `'baichuan-inc/Baichuan2-7B-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`.
|
||||
- `--modelscope`: using **ModelScope** as model hub instead of **Hugging Face**.
|
||||
|
||||
#### Sample Output
|
||||
#### [baichuan-inc/Baichuan2-7B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat)
|
||||
|
|
|
|||
|
|
@ -19,7 +19,6 @@ import time
|
|||
import argparse
|
||||
|
||||
from ipex_llm.transformers import AutoModelForCausalLM
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
# prompt format referred from https://github.com/baichuan-inc/Baichuan2/issues/227
|
||||
# and https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat/blob/main/generation_utils.py#L7-L49
|
||||
|
|
@ -29,14 +28,24 @@ BAICHUAN_PROMPT_FORMAT = "<reserved_106> {prompt} <reserved_107>"
|
|||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for Baichuan model')
|
||||
parser.add_argument('--repo-id-or-model-path', type=str, default="baichuan-inc/Baichuan2-7B-Chat",
|
||||
help='The huggingface repo id for the Baichuan model to be downloaded'
|
||||
', or the path to the huggingface checkpoint folder')
|
||||
help='The Hugging Face repo id for the Baichuan model to be downloaded'
|
||||
', or the path to the 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')
|
||||
parser.add_argument('--modelscope', action="store_true", default=False,
|
||||
help="Use models from modelscope")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.modelscope:
|
||||
from modelscope import AutoTokenizer
|
||||
model_hub = 'modelscope'
|
||||
else:
|
||||
from transformers import AutoTokenizer
|
||||
model_hub = 'huggingface'
|
||||
|
||||
model_path = args.repo_id_or_model_path
|
||||
|
||||
# Load model in 4 bit,
|
||||
|
|
@ -50,7 +59,8 @@ if __name__ == '__main__':
|
|||
model = AutoModelForCausalLM.from_pretrained(model_path,
|
||||
load_in_4bit=True,
|
||||
trust_remote_code=True,
|
||||
use_cache=True)
|
||||
use_cache=True,
|
||||
model_hub=model_hub)
|
||||
model = model.half().to('xpu')
|
||||
|
||||
# Load tokenizer
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
# MiniCPM
|
||||
In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on MiniCPM models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [openbmb/MiniCPM-2B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16) as a reference MiniCPM model.
|
||||
In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on MiniCPM models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [openbmb/MiniCPM-2B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16) and [openbmb/MiniCPM-1B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-1B-sft-bf16) (or [OpenBMB/MiniCPM-2B-sft-bf16](https://www.modelscope.cn/models/OpenBMB/MiniCPM-2B-sft-bf16) and [OpenBMB/MiniCPM-1B-sft-bf16](https://www.modelscope.cn/models/OpenBMB/MiniCPM-1B-sft-bf16) for ModelScope) as a reference MiniCPM 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.
|
||||
|
|
@ -15,6 +15,9 @@ 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/
|
||||
pip install "transformers>=4.36"
|
||||
|
||||
# [optional] only needed if you would like to use ModelScope as model hub
|
||||
pip install modelscope==1.11.0
|
||||
```
|
||||
|
||||
#### 1.2 Installation on Windows
|
||||
|
|
@ -26,6 +29,9 @@ 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/
|
||||
pip install "transformers>=4.36"
|
||||
|
||||
# [optional] only needed if you would like to use ModelScope as model hub
|
||||
pip install modelscope==1.11.0
|
||||
```
|
||||
|
||||
### 2. Configures OneAPI environment variables for Linux
|
||||
|
|
@ -93,14 +99,19 @@ set SYCL_CACHE_PERSISTENT=1
|
|||
> 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?'
|
||||
```bash
|
||||
# for Hugging Face model hub
|
||||
python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT
|
||||
|
||||
# for ModelScope model hub
|
||||
python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT --modelscope
|
||||
```
|
||||
|
||||
Arguments info:
|
||||
- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the MiniCPM model (e.g. `openbmb/MiniCPM-2B-sft-bf16`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'openbmb/MiniCPM-2B-sft-bf16'`.
|
||||
- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the **Hugging Face** or **ModelScope** repo id for the MiniCPM model (e.g. `openbmb/MiniCPM-2B-sft-bf16` or `openbmb/MiniCPM-1B-sft-bf16`) to be downloaded, or the path to the checkpoint folder. It is default to be `'openbmb/MiniCPM-2B-sft-bf16'` for **Hugging Face** and `'OpenBMB/MiniCPM-2B-sft-bf16'` for **ModelScope**.
|
||||
- `--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`.
|
||||
- `--modelscope`: using **ModelScope** as model hub instead of **Hugging Face**.
|
||||
|
||||
#### Sample Output
|
||||
#### [openbmb/MiniCPM-2B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16)
|
||||
|
|
@ -112,3 +123,12 @@ Inference time: xxxx s
|
|||
-------------------- Output --------------------
|
||||
<s> <用户>what is AI?<AI> AI, or Artificial Intelligence, refers to the simulation of human intelligence in machines that are programmed to think and learn like humans. It is a field of computer science
|
||||
```
|
||||
|
||||
#### [openbmb/MiniCPM-1B-sft-bf16](https://huggingface.co/openbmb/MiniCPM-1B-sft-bf16)
|
||||
|
||||
```log
|
||||
-------------------- Prompt --------------------
|
||||
<用户>What is AI?<AI>
|
||||
-------------------- Output --------------------
|
||||
<s> <用户>What is AI?<AI> Artificial Intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think and learn like humans. It involves the development of computer systems that
|
||||
```
|
||||
|
|
@ -19,22 +19,32 @@ import time
|
|||
import argparse
|
||||
|
||||
from ipex_llm.transformers import AutoModelForCausalLM
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for MiniCPM model')
|
||||
parser.add_argument('--repo-id-or-model-path', type=str, default="openbmb/MiniCPM-2B-sft-bf16",
|
||||
help='The huggingface repo id for the MiniCPM model to be downloaded'
|
||||
', or the path to the huggingface checkpoint folder')
|
||||
parser.add_argument('--repo-id-or-model-path', type=str,
|
||||
help='The Hugging Face or ModelScope repo id for the MiniCPM model to be downloaded'
|
||||
', or the path to the checkpoint folder')
|
||||
parser.add_argument('--prompt', type=str, default="What is AI?",
|
||||
help='Prompt to infer')
|
||||
parser.add_argument('--n-predict', type=int, default=32,
|
||||
help='Max tokens to predict')
|
||||
parser.add_argument('--modelscope', action="store_true", default=False,
|
||||
help="Use models from modelscope")
|
||||
|
||||
args = parser.parse_args()
|
||||
model_path = args.repo_id_or_model_path
|
||||
|
||||
if args.modelscope:
|
||||
from modelscope import AutoTokenizer
|
||||
model_hub = 'modelscope'
|
||||
else:
|
||||
from transformers import AutoTokenizer
|
||||
model_hub = 'huggingface'
|
||||
|
||||
model_path = args.repo_id_or_model_path if args.repo_id_or_model_path else \
|
||||
("OpenBMB/MiniCPM-2B-sft-bf16" if args.modelscope else "openbmb/MiniCPM-2B-sft-bf16")
|
||||
|
||||
# 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.
|
||||
|
|
@ -43,9 +53,10 @@ if __name__ == '__main__':
|
|||
load_in_4bit=True,
|
||||
trust_remote_code=True,
|
||||
optimize_model=True,
|
||||
use_cache=True)
|
||||
use_cache=True,
|
||||
model_hub=model_hub)
|
||||
|
||||
model = model.to('xpu')
|
||||
model = model.half().to('xpu')
|
||||
|
||||
# Load tokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path,
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
# MiniCPM3
|
||||
In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on MiniCPM3 models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [openbmb/MiniCPM3-4B](https://huggingface.co/openbmb/MiniCPM3-4B) as a reference MiniCPM3 model.
|
||||
In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on MiniCPM3 models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [openbmb/MiniCPM3-4B](https://huggingface.co/openbmb/MiniCPM3-4B) (or [OpenBMB/MiniCPM3-4B](https://www.modelscope.cn/models/OpenBMB/MiniCPM3-4B) for ModelScope) as a reference MiniCPM3 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.
|
||||
|
|
@ -16,6 +16,9 @@ conda activate llm
|
|||
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
||||
|
||||
pip install jsonschema datamodel_code_generator
|
||||
|
||||
# [optional] only needed if you would like to use ModelScope as model hub
|
||||
pip install modelscope==1.11.0
|
||||
```
|
||||
|
||||
#### 1.2 Installation on Windows
|
||||
|
|
@ -28,6 +31,9 @@ conda activate llm
|
|||
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
|
||||
|
||||
pip install jsonschema datamodel_code_generator
|
||||
|
||||
# [optional] only needed if you would like to use ModelScope as model hub
|
||||
pip install modelscope==1.11.0
|
||||
```
|
||||
|
||||
### 2. Configures OneAPI environment variables for Linux
|
||||
|
|
@ -95,14 +101,19 @@ set SYCL_CACHE_PERSISTENT=1
|
|||
> 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?'
|
||||
```bash
|
||||
# for Hugging Face model hub
|
||||
python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT
|
||||
|
||||
# for ModelScope model hub
|
||||
python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT --modelscope
|
||||
```
|
||||
|
||||
Arguments info:
|
||||
- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the MiniCPM3 model (e.g. `openbmb/MiniCPM3-4B`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'openbmb/MiniCPM3-4B'`.
|
||||
- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the **Hugging Face** or **ModelScope** repo id for the MiniCPM3 model (e.g. `openbmb/MiniCPM3-4B`) to be downloaded, or the path to the checkpoint folder. It is default to be `'openbmb/MiniCPM3-4B'` for **Hugging Face** or `'OpenBMB/MiniCPM3-4B'` for **ModelScope**.
|
||||
- `--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`.
|
||||
- `--modelscope`: using **ModelScope** as model hub instead of **Hugging Face**.
|
||||
|
||||
#### Sample Output
|
||||
#### [openbmb/MiniCPM3-4B](https://huggingface.co/openbmb/MiniCPM3-4B)
|
||||
|
|
|
|||
|
|
@ -19,21 +19,31 @@ import time
|
|||
import argparse
|
||||
|
||||
from ipex_llm.transformers import AutoModelForCausalLM
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for MiniCPM3 model')
|
||||
parser.add_argument('--repo-id-or-model-path', type=str, default="openbmb/MiniCPM3-4B",
|
||||
help='The huggingface repo id for the MiniCPM3 model to be downloaded'
|
||||
', or the path to the huggingface checkpoint folder')
|
||||
parser.add_argument('--repo-id-or-model-path', type=str,
|
||||
help='The Hugging Face or ModelScope repo id for the MiniCPM3 model to be downloaded'
|
||||
', or the path to the checkpoint folder')
|
||||
parser.add_argument('--prompt', type=str, default="What is AI?",
|
||||
help='Prompt to infer')
|
||||
parser.add_argument('--n-predict', type=int, default=32,
|
||||
help='Max tokens to predict')
|
||||
parser.add_argument('--modelscope', action="store_true", default=False,
|
||||
help="Use models from modelscope")
|
||||
|
||||
args = parser.parse_args()
|
||||
model_path = args.repo_id_or_model_path
|
||||
|
||||
if args.modelscope:
|
||||
from modelscope import AutoTokenizer
|
||||
model_hub = 'modelscope'
|
||||
else:
|
||||
from transformers import AutoTokenizer
|
||||
model_hub = 'huggingface'
|
||||
|
||||
model_path = args.repo_id_or_model_path if args.repo_id_or_model_path else \
|
||||
("OpenBMB/MiniCPM3-4B" if args.modelscope else "openbmb/MiniCPM3-4B")
|
||||
|
||||
# Load model in 4 bit,
|
||||
# which convert the relevant layers in the model into INT4 format
|
||||
|
|
@ -43,7 +53,8 @@ if __name__ == '__main__':
|
|||
load_in_4bit=True,
|
||||
trust_remote_code=True,
|
||||
optimize_model=True,
|
||||
use_cache=True)
|
||||
use_cache=True,
|
||||
model_hub=model_hub)
|
||||
|
||||
model = model.half().to('xpu')
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue