Update README.md

2025-02-12 01:43:06 +08:00
parent f629995801
commit c245190a81
33 changed files with 154262 additions and 61 deletions
--- a/README.md
+++ b/README.md
@@ -1,47 +1,222 @@
 ---
-license: Apache License 2.0
-
-#model-type:
-##如 gpt、phi、llama、chatglm、baichuan 等
-#- gpt
-
-#domain:
-##如 nlp、cv、audio、multi-modal
-#- nlp
-
-#language:
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
-#- cn 
-
-#metrics:
-##如 CIDEr、Blue、ROUGE 等
-#- CIDEr
-
-#tags:
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
-#- pretrained
-
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
+license: apache-2.0
+datasets:
+- AIDC-AI/Ovis-dataset
+library_name: transformers
+tags:
+- MLLM
+pipeline_tag: image-text-to-text
+language:
+- en
+- zh
 ---
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型

-SDK下载
+# Ovis2-34B
+<div align="center">
+  <img src=https://cdn-uploads.huggingface.co/production/uploads/637aebed7ce76c3b834cea37/3IK823BZ8w-mz_QfeYkDn.png width="30%"/>
+</div>
+
+## Introduction
+[GitHub](https://github.com/AIDC-AI/Ovis) | [Paper](https://arxiv.org/abs/2405.20797) 
+
+We are pleased to announce the release of **Ovis2**, our latest advancement in multi-modal large language models (MLLMs). Ovis2 inherits the innovative architectural design of the Ovis series, aimed at structurally aligning visual and textual embeddings. As the successor to Ovis1.6, Ovis2 incorporates significant improvements in both dataset curation and training methodologies.
+
+**Key Features**:
+
+- **Small Model Performance**: Optimized training strategies enable small-scale models to achieve higher capability density, demonstrating cross-tier leading advantages.
+
+- **Enhanced Reasoning Capabilities**: Significantly strengthens Chain-of-Thought (CoT) reasoning abilities through the combination of instruction tuning and preference learning.
+
+- **Video and Multi-Image Processing**: Video and multi-image data are incorporated into training to enhance the ability to handle complex visual information across frames and images.
+
+- **Multilingual Support and OCR**: Enhances multilingual OCR beyond English and Chinese and improves structured data extraction from complex visual elements like tables and charts.
+
+<div align="center">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/658a8a837959448ef5500ce5/TIlymOb86R6_Mez3bpmcB.png" width="100%" />
+</div>
+
+## Model Zoo
+
+| Ovis MLLMs |           ViT           |          LLM          |                      Model Weights                      |                           Demo                           |
+|:-----------|:-----------------------:|:---------------------:|:-------------------------------------------------------:|:--------------------------------------------------------:|
+| Ovis2-1B   | aimv2-large-patch14-448 | Qwen2.5-0.5B-Instruct | [Huggingface](https://huggingface.co/AIDC-AI/Ovis2-1B)  | [Space](https://huggingface.co/spaces/AIDC-AI/Ovis2-1B)  |
+| Ovis2-2B   | aimv2-large-patch14-448 | Qwen2.5-1.5B-Instruct | [Huggingface](https://huggingface.co/AIDC-AI/Ovis2-2B)  | [Space](https://huggingface.co/spaces/AIDC-AI/Ovis2-2B)  |
+| Ovis2-4B   | aimv2-huge-patch14-448  |  Qwen2.5-3B-Instruct  | [Huggingface](https://huggingface.co/AIDC-AI/Ovis2-4B)  | [Space](https://huggingface.co/spaces/AIDC-AI/Ovis2-4B)  |
+| Ovis2-8B   | aimv2-huge-patch14-448  |  Qwen2.5-7B-Instruct  | [Huggingface](https://huggingface.co/AIDC-AI/Ovis2-8B)  | [Space](https://huggingface.co/spaces/AIDC-AI/Ovis2-8B)  |
+| Ovis2-16B  | aimv2-huge-patch14-448  | Qwen2.5-14B-Instruct  | [Huggingface](https://huggingface.co/AIDC-AI/Ovis2-16B) | [Space](https://huggingface.co/spaces/AIDC-AI/Ovis2-16B) |
+| Ovis2-34B  |  aimv2-1B-patch14-448   | Qwen2.5-32B-Instruct  | [Huggingface](https://huggingface.co/AIDC-AI/Ovis2-34B) |                            -                             |
+
+## Performance
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/637aebed7ce76c3b834cea37/aCuSemmHy_MhrDaBiYfco.png)
+
+|Benchmark|Ovis2-1B|Ovis2-2B|Ovis2-4B|Ovis2-8B|Ovis2-16B|Ovis2-34B|
+|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
+|MMBench-V1.1<sub>test</sub>|68.5|77.2|81.4|83.3|85.2|86.2|
+|MMStar|52.0|59.0|61.7|64.4|66.9|69.4|
+|MMMU<sub>val</sub>|36.0|45.3|48.0|59.0|59.6|65.6|
+|MathVista<sub>testmini</sub>|59.5|64.4|69.1|71.4|74.9|77.0|
+|HallBench<sub>avg</sub>|44.5|50.2|54.0|56.0|55.9|58.8|
+|AI2D<sub>test</sub>|76.8|82.6|85.5|86.8|86.1|88.4|
+|OCRBench|88.7|87.5|91.0|89.3|88.2|89.8|
+|MMVet|50.3|58.6|65.5|68.5|68.4|75.5|
+|Average|59.5|65.6|69.5|72.3|73.1|76.3|
+
+## Usage
+Below is a code snippet demonstrating how to run Ovis with various input types. For additional usage instructions, including inference wrapper and Gradio UI, please refer to [Ovis GitHub](https://github.com/AIDC-AI/Ovis?tab=readme-ov-file#inference).
 ```bash
-#安装ModelScope
-pip install modelscope
+pip install torch==2.4.0 transformers==4.46.2 numpy==1.25.0 pillow==10.3.0
+pip install flash-attn==2.7.0.post2 --no-build-isolation
 ```
 ```python
-#SDK模型下载
-from modelscope import snapshot_download
-model_dir = snapshot_download('AIDC-AI/Ovis2-34B')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/AIDC-AI/Ovis2-34B.git
+import torch
+from PIL import Image
+from transformers import AutoModelForCausalLM
+
+# load model
+model = AutoModelForCausalLM.from_pretrained("AIDC-AI/Ovis2-34B",
+                                             torch_dtype=torch.bfloat16,
+                                             multimodal_max_length=32768,
+                                             trust_remote_code=True).cuda()
+text_tokenizer = model.get_text_tokenizer()
+visual_tokenizer = model.get_visual_tokenizer()
+
+# single-image input
+image_path = '/data/images/example_1.jpg'
+images = [Image.open(image_path)]
+max_partition = 9
+text = 'Describe the image.'
+query = f'<image>\n{text}'
+
+## cot-style input
+# cot_suffix = "Provide a step-by-step solution to the problem, and conclude with 'the answer is' followed by the final solution."
+# image_path = '/data/images/example_1.jpg'
+# images = [Image.open(image_path)]
+# max_partition = 9
+# text = "What's the area of the shape?"
+# query = f'<image>\n{text}\n{cot_suffix}'
+
+## multiple-images input
+# image_paths = [
+#     '/data/images/example_1.jpg',
+#     '/data/images/example_2.jpg',
+#     '/data/images/example_3.jpg'
+# ]
+# images = [Image.open(image_path) for image_path in image_paths]
+# max_partition = 4
+# text = 'Describe each image.'
+# query = '\n'.join([f'Image {i+1}: <image>' for i in range(len(images))]) + '\n' + text
+
+## text-only input
+# images = []
+# max_partition = None
+# text = 'Hello'
+# query = text
+
+# format conversation
+prompt, input_ids, pixel_values = model.preprocess_inputs(query, images, max_partition=max_partition)
+attention_mask = torch.ne(input_ids, text_tokenizer.pad_token_id)
+input_ids = input_ids.unsqueeze(0).to(device=model.device)
+attention_mask = attention_mask.unsqueeze(0).to(device=model.device)
+if pixel_values is not None:
+    pixel_values = pixel_values.to(dtype=visual_tokenizer.dtype, device=visual_tokenizer.device)
+pixel_values = [pixel_values]
+
+# generate output
+with torch.inference_mode():
+    gen_kwargs = dict(
+        max_new_tokens=1024,
+        do_sample=False,
+        top_p=None,
+        top_k=None,
+        temperature=None,
+        repetition_penalty=None,
+        eos_token_id=model.generation_config.eos_token_id,
+        pad_token_id=text_tokenizer.pad_token_id,
+        use_cache=True
+    )
+    output_ids = model.generate(input_ids, pixel_values=pixel_values, attention_mask=attention_mask, **gen_kwargs)[0]
+    output = text_tokenizer.decode(output_ids, skip_special_tokens=True)
+    print(f'Output:\n{output}')
 ```

-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
+<details>
+<summary>Batch Inference</summary>
+
+```python
+import torch
+from PIL import Image
+from transformers import AutoModelForCausalLM
+
+# load model
+model = AutoModelForCausalLM.from_pretrained("AIDC-AI/Ovis2-34B",
+                                             torch_dtype=torch.bfloat16,
+                                             multimodal_max_length=32768,
+                                             trust_remote_code=True).cuda()
+text_tokenizer = model.get_text_tokenizer()
+visual_tokenizer = model.get_visual_tokenizer()
+
+# preprocess inputs
+batch_inputs = [
+    ('/data/images/example_1.jpg', 'What colors dominate the image?'),
+    ('/data/images/example_2.jpg', 'What objects are depicted in this image?'),
+    ('/data/images/example_3.jpg', 'Is there any text in the image?')
+]
+
+batch_input_ids = []
+batch_attention_mask = []
+batch_pixel_values = []
+
+for image_path, text in batch_inputs:
+    image = Image.open(image_path)
+    query = f'<image>\n{text}'
+    prompt, input_ids, pixel_values = model.preprocess_inputs(query, [image], max_partition=9)
+    attention_mask = torch.ne(input_ids, text_tokenizer.pad_token_id)
+    batch_input_ids.append(input_ids.to(device=model.device))
+    batch_attention_mask.append(attention_mask.to(device=model.device))
+    batch_pixel_values.append(pixel_values.to(dtype=visual_tokenizer.dtype, device=visual_tokenizer.device))
+
+batch_input_ids = torch.nn.utils.rnn.pad_sequence([i.flip(dims=[0]) for i in batch_input_ids], batch_first=True,
+                                                  padding_value=0.0).flip(dims=[1])
+batch_input_ids = batch_input_ids[:, -model.config.multimodal_max_length:]
+batch_attention_mask = torch.nn.utils.rnn.pad_sequence([i.flip(dims=[0]) for i in batch_attention_mask],
+                                                       batch_first=True, padding_value=False).flip(dims=[1])
+batch_attention_mask = batch_attention_mask[:, -model.config.multimodal_max_length:]
+
+# generate outputs
+with torch.inference_mode():
+    gen_kwargs = dict(
+        max_new_tokens=1024,
+        do_sample=False,
+        top_p=None,
+        top_k=None,
+        temperature=None,
+        repetition_penalty=None,
+        eos_token_id=model.generation_config.eos_token_id,
+        pad_token_id=text_tokenizer.pad_token_id,
+        use_cache=True
+    )
+    output_ids = model.generate(batch_input_ids, pixel_values=batch_pixel_values, attention_mask=batch_attention_mask,
+                                **gen_kwargs)
+
+for i in range(len(batch_inputs)):
+    output = text_tokenizer.decode(output_ids[i], skip_special_tokens=True)
+    print(f'Output {i + 1}:\n{output}\n')
+```
+</details>
+
+## Citation
+If you find Ovis useful, please consider citing the paper
+```
+@article{lu2024ovis,
+  title={Ovis: Structural Embedding Alignment for Multimodal Large Language Model},
+  author={Shiyin Lu and Yang Li and Qing-Guo Chen and Zhao Xu and Weihua Luo and Kaifu Zhang and Han-Jia Ye},
+  year={2024},
+  journal={arXiv:2405.20797}
+}
+```
+
+## License
+This project is licensed under the [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt) (SPDX-License-Identifier: Apache-2.0).
+
+## Disclaimer
+We used compliance-checking algorithms during the training process, to ensure the compliance of the trained model to the best of our ability. Due to the complexity of the data and the diversity of language model usage scenarios, we cannot guarantee that the model is completely free of copyright issues or improper content. If you believe anything infringes on your rights or generates improper content, please contact us, and we will promptly address the matter.