Add Modelscope option for GPU model chatglm3

python/llm/example/GPU/HuggingFace/LLM/chatglm3/README.md

@@ -23,6 +23,9 @@ 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/
+
+# [optional] if you use modelscope as model hub, please make sure you are using 1.11.0 version
+pip install modelscope==1.11.0
 ```
 
 ## 2. Configures OneAPI environment variables for Linux
@@ -101,6 +104,7 @@ Arguments info:
 - `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the ChatGLM3 model to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'THUDM/chatglm3-6b'`.
 - `--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 **huggingface**.
 
 #### Sample Output
 #### [THUDM/chatglm3-6b](https://huggingface.co/THUDM/chatglm3-6b)
@@ -146,3 +150,4 @@ Arguments info:
 - `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the ChatGLM3 model to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'THUDM/chatglm3-6b'`.
 - `--question QUESTION`: argument defining the question to ask. It is default to be `"晚上睡不着应该怎么办"`.
 - `--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.
+- `--modelscope`: using **Modelscope** as model hub instead of **huggingface**.

python/llm/example/GPU/HuggingFace/LLM/chatglm3/generate.py

@@ -20,24 +20,34 @@
 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://github.com/THUDM/ChatGLM3/blob/main/PROMPT.md
 CHATGLM_V3_PROMPT_FORMAT = "<|user|>\n{prompt}\n<|assistant|>"
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for ChatGLM3 model')
-    parser.add_argument('--repo-id-or-model-path', type=str, default="THUDM/chatglm3-6b",
+    parser.add_argument('--repo-id-or-model-path', type=str, 
                         help='The huggingface repo id for the ChatGLM3 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')
+    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 \
+        ("ZhipuAI/chatglm3-6b" if args.modelscope else "THUDM/chatglm3-6b")
 
     # Load model in 4 bit,
     # which convert the relevant layers in the model into INT4 format
@@ -47,7 +57,8 @@
                                       load_in_4bit=True,
                                       optimize_model=True,
                                       trust_remote_code=True,
-                                      use_cache=True)
+                                      use_cache=True,
+                                      model_hub=model_hub)
     model = model.half().to('xpu')
 
     # Load tokenizer

python/llm/example/GPU/HuggingFace/LLM/chatglm3/streamchat.py

@@ -20,21 +20,32 @@
 import numpy as np
 
 from ipex_llm.transformers import AutoModel
-from transformers import AutoTokenizer
 
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='Stream Chat for ChatGLM3 model')
-    parser.add_argument('--repo-id-or-model-path', type=str, default="THUDM/chatglm3-6b",
+    parser.add_argument('--repo-id-or-model-path', type=str,
                         help='The huggingface repo id for the ChatGLM3 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')
+    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 \
+        ("ZhipuAI/chatglm3-6b" if args.modelscope else "THUDM/chatglm3-6b")
+
     disable_stream = args.disable_stream
 
     # Load model in 4 bit,
@@ -44,7 +55,8 @@
     model = AutoModel.from_pretrained(model_path,
                                       load_in_4bit=True,
                                       trust_remote_code=True,
-                                      optimize_model=True)
+                                      optimize_model=True,
+                                      model_hub=model_hub)
     model.to('xpu')
 
     # Load tokenizer