Update license to MIT and clarify component licenses

README.md

@@ -1,24 +1,24 @@
 ---
-license: apache-2.0
-pipeline_tag: image-text-to-text
-library_name: transformers
 base_model:
-  - OpenGVLab/InternViT-300M-448px-V2_5
-  - Qwen/Qwen3-0.6B
-base_model_relation: merge
+- OpenGVLab/InternViT-300M-448px-V2_5
+- Qwen/Qwen3-0.6B
 datasets:
-  - OpenGVLab/MMPR-v1.2
-  - OpenGVLab/MMPR-Tiny
+- OpenGVLab/MMPR-v1.2
+- OpenGVLab/MMPR-Tiny
 language:
-  - multilingual
+- multilingual
+library_name: transformers
+license: mit
+pipeline_tag: image-text-to-text
 tags:
-  - internvl
-  - custom_code
+- internvl
+- custom_code
+base_model_relation: merge
 ---
 
 # InternVL3_5-1B-Pretrained
 
-[\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL)  [\[📜 InternVL 1.0\]](https://huggingface.co/papers/2312.14238)  [\[📜 InternVL 1.5\]](https://huggingface.co/papers/2404.16821)  [\[📜 InternVL 2.5\]](https://huggingface.co/papers/2412.05271)  [\[📜 InternVL2.5-MPO\]](https://huggingface.co/papers/2411.10442)  [\[📜 InternVL3\]](https://huggingface.co/papers/2504.10479) [\[📜 InternVL3.5\]](https://huggingface.co/papers/2508.18265)
+[\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL)  [\[📜 InternVL 1.0\]](https://huggingface.co/papers/2312.14238)  [\[📜 InternVL 1.5\\]](https://huggingface.co/papers/2404.16821)  [\[📜 InternVL 2.5\]](https://huggingface.co/papers/2412.05271)  [\[📜 InternVL2.5-MPO\]](https://huggingface.co/papers/2411.10442)  [\[📜 InternVL3\]](https://huggingface.co/papers/2504.10479) [\[📜 InternVL3.5\]](https://huggingface.co/papers/2508.18265)
 
 [\[🆕 Blog\]](https://internvl.github.io/blog/)  [\[🗨️ Chat Demo\]](https://chat.intern-ai.org.cn/)  [\[🚀 Quick Start\]](#quick-start)  [\[📖 Documents\]](https://internvl.readthedocs.io/en/latest/)
 
@@ -423,7 +423,7 @@ You are an AI assistant that rigorously follows this response protocol:
 Ensure that the thinking process is thorough but remains focused on the query. The final answer should be standalone and not reference the thinking section.
 """.strip()
 
-model.system_message = R1_SYSTEMP_PROMPT
+model.system_message = R1_SYSTEM_PROMPT
 ```
 
 ### Inference with Transformers
@@ -530,40 +530,50 @@ generation_config = dict(max_new_tokens=1024, do_sample=True)
 # pure-text conversation (纯文本对话)
 question = 'Hello, who are you?'
 response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
+print(f'User: {question}
+Assistant: {response}')
 
 question = 'Can you tell me a story?'
 response, history = model.chat(tokenizer, None, question, generation_config, history=history, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
+print(f'User: {question}
+Assistant: {response}')
 
 # single-image single-round conversation (单图单轮对话)
-question = '<image>\nPlease describe the image shortly.'
+question = '<image>
+Please describe the image shortly.'
 response = model.chat(tokenizer, pixel_values, question, generation_config)
-print(f'User: {question}\nAssistant: {response}')
+print(f'User: {question}
+Assistant: {response}')
 
 # single-image multi-round conversation (单图多轮对话)
-question = '<image>\nPlease describe the image in detail.'
+question = '<image>
+Please describe the image in detail.'
 response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
+print(f'User: {question}
+Assistant: {response}')
 
 question = 'Please write a poem according to the image.'
 response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
+print(f'User: {question}
+Assistant: {response}')
 
 # multi-image multi-round conversation, combined images (多图多轮对话，拼接图像)
 pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
 pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
 pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
 
-question = '<image>\nDescribe the two images in detail.'
+question = '<image>
+Describe the two images in detail.'
 response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                                history=None, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
+print(f'User: {question}
+Assistant: {response}')
 
 question = 'What are the similarities and differences between these two images.'
 response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                                history=history, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
+print(f'User: {question}
+Assistant: {response}')
 
 # multi-image multi-round conversation, separate images (多图多轮对话，独立图像)
 pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
@@ -571,17 +581,21 @@ pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat1
 pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
 num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
 
-question = 'Image-1: <image>\nImage-2: <image>\nDescribe the two images in detail.'
+question = 'Image-1: <image>
+Image-2: <image>
+Describe the two images in detail.'
 response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                                num_patches_list=num_patches_list,
                                history=None, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
+print(f'User: {question}
+Assistant: {response}')
 
 question = 'What are the similarities and differences between these two images.'
 response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                                num_patches_list=num_patches_list,
                                history=history, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
+print(f'User: {question}
+Assistant: {response}')
 
 # batch inference, single image per sample (单图批处理)
 pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
@@ -589,13 +603,15 @@ pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat1
 num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
 pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
 
-questions = ['<image>\nDescribe the image in detail.'] * len(num_patches_list)
+questions = ['<image>
+Describe the image in detail.'] * len(num_patches_list)
 responses = model.batch_chat(tokenizer, pixel_values,
                              num_patches_list=num_patches_list,
                              questions=questions,
                              generation_config=generation_config)
 for question, response in zip(questions, responses):
-    print(f'User: {question}\nAssistant: {response}')
+    print(f'User: {question}
+Assistant: {response}')
 
 # video multi-round conversation (视频多轮对话)
 def get_index(bound, fps, max_frame, first_idx=0, num_segments=32):
@@ -633,17 +649,24 @@ def load_video(video_path, bound=None, input_size=448, max_num=1, num_segments=3
 video_path = './examples/red-panda.mp4'
 pixel_values, num_patches_list = load_video(video_path, num_segments=8, max_num=1)
 pixel_values = pixel_values.to(torch.bfloat16).cuda()
-video_prefix = ''.join([f'Frame{i+1}: <image>\n' for i in range(len(num_patches_list))])
+video_prefix = ''.join([f'Frame{i+1}: <image>
+' for i in range(len(num_patches_list))])
 question = video_prefix + 'What is the red panda doing?'
-# Frame1: <image>\nFrame2: <image>\n...\nFrame8: <image>\n{question}
+# Frame1: <image>
+Frame2: <image>
+...
+Frame8: <image>
+{question}
 response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                                num_patches_list=num_patches_list, history=None, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
+print(f'User: {question}
+Assistant: {response}')
 
 question = 'Describe this video in detail.'
 response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                                num_patches_list=num_patches_list, history=history, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
+print(f'User: {question}
+Assistant: {response}')
 ```
 
 #### Streaming Output
@@ -727,7 +750,9 @@ image_urls=[
 
 images = [load_image(img_url) for img_url in image_urls]
 # Numbering images improves multi-image conversations
-response = pipe((f'Image-1: {IMAGE_TOKEN}\nImage-2: {IMAGE_TOKEN}\ndescribe these two images', images))
+response = pipe((f'Image-1: {IMAGE_TOKEN}
+Image-2: {IMAGE_TOKEN}
+describe these two images', images))
 print(response.text)
 ```
 
@@ -816,7 +841,7 @@ print(response)
 
 ## License
 
-This project is released under the apache-2.0 License. This project uses the pre-trained Qwen3 as a component, which is licensed under the apache-2.0 License.
+This project is released under the [MIT License](https://github.com/OpenGVLab/InternVL/blob/main/LICENSE). Parts of this project, such as the pre-trained Qwen3 component, are licensed under the Apache-2.0 License.
 
 ## Citation
 
@@ -829,4 +854,4 @@ If you find this project useful in your research, please consider citing:
   journal={arXiv preprint arXiv:2508.18265},
   year={2025}
 }
-```
+```