Update README.md


README.md

@@ -9,7 +9,7 @@ pipeline_tag: image-text-to-text
 
 ## Model Overview
 
-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.
+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.
 
 ## 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.
@@ -29,6 +29,9 @@ bf16: true
 flash_attn: fa2
 ```
 
+Training loss curve:
+<img src="https://cdn-uploads.huggingface.co/production/uploads/65af78bb3e82498d4c65ed2a/8BNyo-v68aFvab2kXxtt1.png"/>
+
 ## Usage
 
 You can load the model using the Hugging Face `transformers` library:
@@ -37,7 +40,7 @@ You can load the model using the Hugging Face `transformers` library:
 from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
 import torch
 
-MODEL_ID = "Fancy-MLLM/R1-OneVision-7B"
+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,
@@ -79,9 +82,6 @@ output_text = processor.batch_decode(
 print(output_text)
 ```
 
-Training loss curve:
-<img src=""/>
-
 ## Ongoing Work
 1. **Rule-Based Reinforcement Learning (RL)**