diff for compatibility

README.md

@@ -7,110 +7,22 @@ base_model:
 pipeline_tag: image-text-to-text
 ---
 
-## R1-Onevision
+<!-- header start -->
+<p align="center">
+  <img src="https://huggingface.co/datasets/FriendliAI/documentation-images/resolve/main/model-card-assets/friendliai.png" width="100%" alt="FriendliAI Logo">
+</p>
+<!-- header end -->
 
-[\[📂 GitHub\]](https://github.com/Fancy-MLLM/R1-Onevision)[\[📝 Report\]](https://yangyi-vai.notion.site/r1-onevision?pvs=4)
-[\[🤗 HF Dataset\]](https://huggingface.co/datasets/Fancy-MLLM/R1-onevision)  [\[🤗 Reasoning Benchmark\]](https://huggingface.co/datasets/Fancy-MLLM/R1-OneVision-Bench) [\[🤗 HF Demo\]](https://huggingface.co/spaces/Fancy-MLLM/R1-OneVision)    
 
-## Model Overview
+# Fancy-MLLM/R1-Onevision-7B
 
-This is a multimodal large language model fine-tuned from Qwen2.5-VL on the **R1-Onevision** dataset. The model enhances vision-language understanding and reasoning capabilities, making it suitable for various tasks such as visual reasoning, image understanding. With its robust ability to perform multimodal reasoning, R1-Onevision emerges as a powerful AI assistant capable of addressing a wide range of problem-solving challenges across different domains.
+* Model creator: [Fancy-MLLM](https://huggingface.co/Fancy-MLLM)
+* Original model: [R1-Onevision-7B](https://huggingface.co/Fancy-MLLM/R1-Onevision-7B)
 
-## Training Configuration and Curve
-- Framework: The training process uses the open-source **LLama-Factory** library, with **Qwen2.5-VL-Instruct** as the base model. This model comes in three variants: 3B, 7B, and 32B.
-- Parameters: For efficiency, we use a resolution of 518 for image inputs to save GPU memory. The training follows a full model SFT (Supervised Fine-Tuning) approach with a learning rate of 1e-5, trained for one epoch.
-    
-The training configuration is as follows:
-```python
-image_resolution: 518
-cutoff_len: 8192
-per_device_train_batch_size: 1
-gradient_accumulation_steps: 16
-learning_rate: 1.0e-5
+## Differences
 
-num_train_epochs: 1.0
-lr_scheduler_type: cosine
-warmup_ratio: 0.05
-bf16: true
-flash_attn: fa2
-```
+* Fixed the incorrectly set image_processor_type in preprocessor_config.json.
 
-Training loss curve:
-<img src="https://cdn-uploads.huggingface.co/production/uploads/65af78bb3e82498d4c65ed2a/8BNyo-v68aFvab2kXxtt1.png"/>
+## License
 
-## Usage
-
-You can load the model using the Hugging Face `transformers` library:
-
-```python
-from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
-import torch
-from qwen_vl_utils import process_vision_info
-
-MODEL_ID = "Fancy-MLLM/R1-Onevision-7B"
-processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
-model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
-    MODEL_ID,
-    trust_remote_code=True,
-    torch_dtype=torch.bfloat16
-).to("cuda").eval()
-
-messages = [
-    {
-        "role": "user",
-        "content": [
-            {"type": "image", "image": "<your image path>"},
-            {"type": "text", "text": "Hint: Please answer the question and provide the final answer at the end. Question: Which number do you have to write in the last daisy?"},
-        ],
-    }
-]
-
-# Preparation for inference
-text = processor.apply_chat_template(
-    messages, tokenize=False, add_generation_prompt=True
-)
-image_inputs, video_inputs = process_vision_info(messages)
-inputs = processor(
-    text=[text],
-    images=image_inputs,
-    videos=video_inputs,
-    padding=True,
-    return_tensors="pt",
-)
-inputs = inputs.to(model.device)
-
-generated_ids = model.generate(**inputs, max_new_tokens=4096)
-generated_ids_trimmed = [
-    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
-]
-output_text = processor.batch_decode(
-    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
-)
-print(output_text)
-```
-
-## Ongoing Work
-1. **Rule-Based Reinforcement Learning (RL)**
-    
-    We are actively exploring the integration of rule-based systems into reinforcement learning to enhance the agent's decision-making process. This approach combines domain-specific rules with the learning process, aiming to improve the efficiency and safety of learning in complex environments.
-    
-2. **Training with General Data and Multimodal Reasoning CoT**
-    
-    Our ongoing work includes expanding the training datasets by incorporating more general data alongside multimodal reasoning Chain-of-Thought (CoT) data. This will enable the model to benefit from a broader range of information, enhancing its ability to handle diverse reasoning tasks across various domains.
-    
-3. **Incorporating Chinese Multimodal Reasoning CoT Data**
-    
-    We are also focused on integrating Chinese multimodal reasoning CoT data into the training process. By adding this language-specific dataset, we aim to improve the model’s capability to perform reasoning tasks in Chinese, expanding its multilingual and multimodal reasoning proficiency.
-    
-4. **Release of the 3B Model**
-
-    
-    We are working on the release of a smaller, more efficient 3B model, which is designed to provide a balance between performance and resource efficiency. This model aims to deliver strong multimodal reasoning capabilities while being more accessible and optimized for environments with limited computational resources, offering a more compact alternative to the current 7B model.
-
-# Institution
-- Zhejiang University
-
-## Model Contact
-- [email protected]
-- [email protected]
-- [email protected]
+Refer to the license of the original model card.

preprocessor_config.json

@@ -8,7 +8,7 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "Qwen2_5_VLImageProcessor",
+  "image_processor_type": "Qwen2VLImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,
@@ -26,4 +26,4 @@
     "shortest_edge": 3136
   },
   "temporal_patch_size": 2
-}
+}