minicpm-v-2_6:don't use model_hub=modelscope when use lowbit; internvl2

intel-analytics · Dec 20, 2024 · 409f8f5 · 409f8f5
1 parent 7803eda
commit 409f8f5
Show file tree

Hide file tree

Showing 3 changed files with 34 additions and 12 deletions.
diff --git a/python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2_6/chat.py b/python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2_6/chat.py
@@ -22,6 +22,7 @@
 import torch
 from PIL import Image
 from ipex_llm.transformers import AutoModel
+from transformers import AutoProcessor
 
 
 if __name__ == '__main__':
@@ -49,10 +50,10 @@
     args = parser.parse_args()
 
     if args.modelscope:
-        from modelscope import AutoTokenizer, AutoProcessor
+        from modelscope import AutoTokenizer
         model_hub = 'modelscope'
     else:
-        from transformers import AutoTokenizer, AutoProcessor
+        from transformers import AutoTokenizer
         model_hub = 'huggingface'
 
     model_path = args.repo_id_or_model_path if args.repo_id_or_model_path else \
@@ -81,8 +82,7 @@
                                        optimize_model=True,
                                        trust_remote_code=True,
                                        use_cache=True,
-                                       modules_to_not_convert=["vpm", "resampler"],
-                                       model_hub=model_hub)
+                                       modules_to_not_convert=["vpm", "resampler"])
         tokenizer = AutoTokenizer.from_pretrained(lowbit_path,
                                                   trust_remote_code=True)
 

diff --git a/python/llm/example/GPU/HuggingFace/Multimodal/internvl2/chat.py b/python/llm/example/GPU/HuggingFace/Multimodal/internvl2/chat.py
@@ -22,22 +22,32 @@
 import torch
 from PIL import Image
 from ipex_llm.transformers import AutoModelForCausalLM
-from transformers import AutoTokenizer, CLIPImageProcessor
+from transformers import CLIPImageProcessor
 
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='Predict Tokens using `chat()` API for OpenGVLab/InternVL2-4B model')
     parser.add_argument('--repo-id-or-model-path', type=str, default="OpenGVLab/InternVL2-4B",
-                        help='The huggingface repo id for the OpenGVLab/InternVL2-4B model to be downloaded'
-                             ', or the path to the huggingface checkpoint folder')
+                        help='The Hugging Face or ModelScope repo id for the InternVL2 model to be downloaded'
+                             ', or the path to the checkpoint folder')
     parser.add_argument('--image-url-or-path', type=str,
                         default='https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg',
                         help='The URL or path to the image to infer')
     parser.add_argument('--prompt', type=str, default="What is in the image?",
                         help='Prompt to infer')
     parser.add_argument('--n-predict', type=int, default=64, 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
     image_path = args.image_url_or_path
     n_predict = args.n_predict
@@ -48,7 +58,8 @@
     # This will allow the memory-intensive embedding layer to utilize the CPU instead of iGPU.
     model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True,
                                                  load_in_low_bit="sym_int4",
-                                                 modules_to_not_convert=["vision_model"])
+                                                 modules_to_not_convert=["vision_model"],
+                                                 model_hub=model_hub)
     model = model.half().to('xpu')
     tokenizer = AutoTokenizer.from_pretrained(model_path,
                                               trust_remote_code=True)

diff --git a/python/llm/example/GPU/HuggingFace/Multimodal/internvl2/readme.md b/python/llm/example/GPU/HuggingFace/Multimodal/internvl2/readme.md
@@ -1,5 +1,5 @@
 # InternVL2
-In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on InternVL2 model on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [OpenGVLab/InternVL2-4B](https://huggingface.co/OpenGVLab/InternVL2-4B) as a reference InternVL2 model.
+In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on InternVL2 model on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [OpenGVLab/InternVL2-4B](https://huggingface.co/OpenGVLab/InternVL2-4B) (or [OpenGVLab/InternVL2-4B](https://www.modelscope.cn/models/OpenGVLab/InternVL2-4B) for ModelScope) as a reference InternVL2 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.
@@ -17,6 +17,9 @@ pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-exte
 
 pip install einops timm
 
+# [optional] only needed if you would like to use ModelScope as model hub
+pip install modelscope==1.11.0
+
 ```
 
 #### 1.2 Installation on Windows
@@ -30,6 +33,9 @@ pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-exte
 
 pip install einops timm
 
+# [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
@@ -98,15 +104,20 @@ set SYCL_CACHE_PERSISTENT=1
 ### 4. Running examples
 
 - chat with specified prompt:
-  ```
-  python ./chat.py --prompt 'What is in the image?'
+  ```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 --image-url-or-path IMAGE_URL_OR_PATH
+
+  # for ModelScope model hub
+  python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT --image-url-or-path IMAGE_URL_OR_PATH --modelscope
   ```
 
 Arguments info:
-- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the InternVL2 (e.g. `OpenGVLab/InternVL2-4B`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'OpenGVLab/InternVL2-4B'`.
+- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the **Hugging Face** or **ModelScope** repo id for the InternVL2 (e.g. `OpenGVLab/InternVL2-4B`) to be downloaded, or the path to the checkpoint folder. It is default to be `'OpenGVLab/InternVL2-4B'`.
 - `--image-url-or-path IMAGE_URL_OR_PATH`: argument defining the image to be infered. It is default to be `'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg'`.
 - `--prompt PROMPT`: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be `'What is in the image?'`.
 - `--n-predict N_PREDICT`: argument defining the max number of tokens to predict. It is default to be `64`.
+- `--modelscope`: using **ModelScope** as model hub instead of **Hugging Face**.
 
 #### Sample Output