MiniCPM-V-2 & MiniCPM-Llama3-V-2_5 example updates (#11988)

* minicpm example updates

* --stream

python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-Llama3-V-2_5/README.md

@@ -5,7 +5,7 @@ In this directory, you will find examples on how you could apply IPEX-LLM INT4 o
 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 `chat()` API
-In the example [generate.py](./generate.py), we show a basic use case for a MiniCPM-Llama3-V-2_5 model to predict the next N tokens using `chat()` API, with IPEX-LLM INT4 optimizations on Intel GPUs.
+In the example [chat.py](./chat.py), we show a basic use case for a MiniCPM-Llama3-V-2_5 model to predict the next N tokens using `chat()` API, with IPEX-LLM INT4 optimizations on Intel GPUs.
 ### 1. Install
 #### 1.1 Installation on Linux
 We suggest using conda to manage environment:
@@ -106,15 +106,20 @@ 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
 
+- chat without streaming mode:
   ```
-python ./generate.py --prompt 'What is in the image?'
+  python ./chat.py --prompt 'What is in the image?'
+  ```
+- chat in streaming mode:
+  ```
+  python ./chat.py --prompt 'What is in the image?' --stream
   ```
 
 Arguments info:
 - `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the MiniCPM-Llama3-V-2_5 (e.g. `openbmb/MiniCPM-Llama3-V-2_5`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'openbmb/MiniCPM-Llama3-V-2_5'`.
 - `--image-url-or-path IMAGE_URL_OR_PATH`: argument defining the image to be infered. It is default to be `'http://farm6.staticflickr.com/5268/5602445367_3504763978_z.jpg'`.
 - `--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 `32`.
+- `--stream`: flag to chat in streaming mode
 
 #### Sample Output
 
@@ -122,12 +127,21 @@ Arguments info:
 
 ```log
 Inference time: xxxx s
--------------------- Input --------------------
+-------------------- Input Image --------------------
 http://farm6.staticflickr.com/5268/5602445367_3504763978_z.jpg
--------------------- Prompt --------------------
+-------------------- Input Prompt --------------------
 What is in the image?
--------------------- Output --------------------
+-------------------- Chat Output --------------------
-The image features a young child holding a white teddy bear. The teddy bear is dressed in a pink outfit. The child appears to be outdoors, with a stone wall and some red flowers in the background.
+The image features a young child holding a white teddy bear. The teddy bear is dressed in a pink dress with a ribbon on it. The child appears to be smiling and enjoying the moment.
+```
+```log
+Inference time: xxxx s
+-------------------- Input Image --------------------
+http://farm6.staticflickr.com/5268/5602445367_3504763978_z.jpg
+-------------------- Input Prompt --------------------
+图片里有什么？
+-------------------- Chat Output --------------------
+图片中有一个小孩，手里拿着一个白色的玩具熊。这个孩子看起来很开心，正在微笑并与玩具互动。背景包括红色的花朵和石墙，为这个场景增添了色彩和质感。
 ```
 
 The sample input image is (which is fetched from [COCO dataset](https://cocodataset.org/#explore?id=264959)):

python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-Llama3-V-2_5/chat.py

@@ -14,10 +14,12 @@
 # limitations under the License.
 #
 
+
 import os
 import time
 import argparse
 import requests
+import torch
 from PIL import Image
 from ipex_llm.transformers import AutoModel
 from transformers import AutoTokenizer
@@ -33,8 +35,8 @@ if __name__ == '__main__':
                         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=32,
+    parser.add_argument('--stream', action='store_true',
-                        help='Max tokens to predict')
+                        help='Whether to chat in streaming mode')
 
     args = parser.parse_args()
     model_path = args.repo_id_or_model_path
@@ -45,11 +47,12 @@ if __name__ == '__main__':
     # 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,
+                                      load_in_low_bit="sym_int4",
-                                      optimize_model=False,
+                                      optimize_model=True,
                                       trust_remote_code=True,
-                                      use_cache=True)
+                                      use_cache=True,
-    model = model.half().to(device='xpu')
+                                      modules_to_not_convert=["vpm", "resampler"])
+    model = model.half().to('xpu')
     tokenizer = AutoTokenizer.from_pretrained(model_path,
                                               trust_remote_code=True)
     model.eval()
@@ -61,23 +64,45 @@ if __name__ == '__main__':
        image = Image.open(requests.get(image_path, stream=True).raw).convert('RGB')
 
     # Generate predicted tokens
-    # here the prompt tuning refers to https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5/blob/main/README.md
+    # here the prompt tuning refers to https://huggingface.co/openbmb/MiniCPM-V-2_6/blob/main/README.md
-    msgs = [{'role': 'user', 'content': args.prompt}]
+    msgs = [{'role': 'user', 'content': [image, args.prompt]}]
+
+    # ipex_llm model needs a warmup, then inference time can be accurate
+    model.chat(
+        image=None,
+        msgs=msgs,
+        tokenizer=tokenizer,
+    )
+
+    if args.stream:
+        res = model.chat(
+            image=None,
+            msgs=msgs,
+            tokenizer=tokenizer,
+            stream=True
+        )
+
+        print('-'*20, 'Input Image', '-'*20)
+        print(image_path)
+        print('-'*20, 'Input Prompt', '-'*20)
+        print(args.prompt)
+        print('-'*20, 'Stream Chat Output', '-'*20)
+        for new_text in res:
+            print(new_text, flush=True, end='')
+    else:
         st = time.time()
         res = model.chat(
-     image=image,
+            image=None,
             msgs=msgs,
-     context=None,
             tokenizer=tokenizer,
-     sampling=False,
-     temperature=0.7
         )
+        torch.xpu.synchronize()
         end = time.time()
+
         print(f'Inference time: {end-st} s')
-    print('-'*20, 'Input', '-'*20)
+        print('-'*20, 'Input Image', '-'*20)
         print(image_path)
-    print('-'*20, 'Prompt', '-'*20)
+        print('-'*20, 'Input Prompt', '-'*20)
         print(args.prompt)
-    output_str = res
+        print('-'*20, 'Chat Output', '-'*20)
-    print('-'*20, 'Output', '-'*20)
+        print(res)
-    print(output_str)

python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2/README.md

@@ -5,7 +5,7 @@ In this directory, you will find examples on how you could apply IPEX-LLM INT4 o
 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 `chat()` API
-In the example [generate.py](./generate.py), we show a basic use case for a MiniCPM-V-2 model to predict the next N tokens using `chat()` API, with IPEX-LLM INT4 optimizations on Intel GPUs.
+In the example [chat.py](./chat.py), we show a basic use case for a MiniCPM-V-2 model to predict the next N tokens using `chat()` API, with IPEX-LLM INT4 optimizations on Intel GPUs.
 ### 1. Install
 #### 1.1 Installation on Linux
 We suggest using conda to manage environment:
@@ -106,15 +106,20 @@ 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
 
+- chat without streaming mode:
   ```
-python ./generate.py --prompt 'What is in the image?'
+  python ./chat.py --prompt 'What is in the image?'
+  ```
+- chat in streaming mode:
+  ```
+  python ./chat.py --prompt 'What is in the image?' --stream
   ```
 
 Arguments info:
 - `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the MiniCPM-V-2 (e.g. `openbmb/MiniCPM-V-2`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'openbmb/MiniCPM-V-2'`.
 - `--image-url-or-path IMAGE_URL_OR_PATH`: argument defining the image to be infered. It is default to be `'http://farm6.staticflickr.com/5268/5602445367_3504763978_z.jpg'`.
 - `--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 `32`.
+- `--stream`: flag to chat in streaming mode
 
 #### Sample Output
 
@@ -122,12 +127,20 @@ Arguments info:
 
 ```log
 Inference time: xxxx s
--------------------- Input --------------------
+-------------------- Input Image --------------------
 http://farm6.staticflickr.com/5268/5602445367_3504763978_z.jpg
--------------------- Prompt --------------------
+-------------------- Input Prompt --------------------
 What is in the image?
--------------------- Output --------------------
+-------------------- Chat Output --------------------
-In the image, there is a young child holding a teddy bear. The teddy bear appears to be dressed in a pink tutu. The child is also wearing a red and white striped dress. The background of the image includes a stone wall and some red flowers.
+In the image, there is a young child holding a teddy bear. The teddy bear is dressed in a pink tutu. The child is also wearing a red and white striped dress. The background of the image features a stone wall and some red flowers.
+```
+```log
+-------------------- Input Image --------------------
+http://farm6.staticflickr.com/5268/5602445367_3504763978_z.jpg
+-------------------- Input Prompt --------------------
+图片里有什么？
+-------------------- Chat Output --------------------
+图中是一个小女孩，她手里拿着一只粉白相间的泰迪熊。
 ```
 
 The sample input image is (which is fetched from [COCO dataset](https://cocodataset.org/#explore?id=264959)):

python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2/chat.py

@@ -15,6 +15,7 @@
 #
 
 
+
 from typing import List, Tuple, Optional, Union
 import math
 import timm
@@ -110,6 +111,7 @@ import os
 import time
 import argparse
 import requests
+import torch
 from PIL import Image
 from ipex_llm.transformers import AutoModel
 from transformers import AutoTokenizer
@@ -125,8 +127,8 @@ if __name__ == '__main__':
                         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=32,
+    parser.add_argument('--stream', action='store_true',
-                        help='Max tokens to predict')
+                        help='Whether to chat in streaming mode')
 
     args = parser.parse_args()
     model_path = args.repo_id_or_model_path
@@ -140,9 +142,9 @@ if __name__ == '__main__':
                                       load_in_low_bit="asym_int4",
                                       optimize_model=True,
                                       trust_remote_code=True,
-                                      modules_to_not_convert=["vpm", "resampler", "lm_head"],
+                                      use_cache=True,
-                                      use_cache=True)
+                                      modules_to_not_convert=["vpm", "resampler"])
-    model = model.half().to(device='xpu')
+    model = model.half().to('xpu')
     tokenizer = AutoTokenizer.from_pretrained(model_path,
                                               trust_remote_code=True)
     model.eval()
@@ -156,6 +158,34 @@ if __name__ == '__main__':
     # Generate predicted tokens
     # here the prompt tuning refers to https://huggingface.co/openbmb/MiniCPM-V-2/blob/main/README.md
     msgs = [{'role': 'user', 'content': args.prompt}]
+
+    # ipex_llm model needs a warmup, then inference time can be accurate
+    res, context, _ = model.chat(
+     image=image,
+     msgs=msgs,
+     context=None,
+     tokenizer=tokenizer,
+     sampling=False,
+     temperature=0.7
+    )
+    if args.stream:
+        res, context, _ = model.chat(
+        image=image,
+        msgs=msgs,
+        context=None,
+        tokenizer=tokenizer,
+        sampling=False,
+        temperature=0.7
+        )
+
+        print('-'*20, 'Input Image', '-'*20)
+        print(image_path)
+        print('-'*20, 'Input Prompt', '-'*20)
+        print(args.prompt)
+        print('-'*20, 'Stream Chat Output', '-'*20)
+        for new_text in res:
+            print(new_text, flush=True, end='')
+    else:
         st = time.time()
         res, context, _ = model.chat(
         image=image,
@@ -165,12 +195,13 @@ if __name__ == '__main__':
         sampling=False,
         temperature=0.7
         )
+        torch.xpu.synchronize()
         end = time.time()
+
         print(f'Inference time: {end-st} s')
-    print('-'*20, 'Input', '-'*20)
+        print('-'*20, 'Input Image', '-'*20)
         print(image_path)
-    print('-'*20, 'Prompt', '-'*20)
+        print('-'*20, 'Input Prompt', '-'*20)
         print(args.prompt)
-    output_str = res
+        print('-'*20, 'Chat Output', '-'*20)
-    print('-'*20, 'Output', '-'*20)
+        print(res)
-    print(output_str)

python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2_6/README.md

@@ -108,11 +108,11 @@ set SYCL_CACHE_PERSISTENT=1
 
 - chat without streaming mode:
   ```
-  python ./generate.py --prompt 'What is in the image?'
+  python ./chat.py --prompt 'What is in the image?'
   ```
 - chat in streaming mode:
   ```
-  python ./generate.py --prompt 'What is in the image?' --stream
+  python ./chat.py --prompt 'What is in the image?' --stream
   ```
 
 > [!TIP]