Update README.md

README.md

@@ -11,40 +11,57 @@ library_name: transformers
 ---
 # LLaVA-OneVision-1.5: Fully Open-Source State-of-the-Art VLM Model
 
-# ✨ Key Features
+## Introduction
+**LLaVA-OneVision1.5** introduces a novel family of **fully open-source** Large Multimodal Models (LMMs) that achieves **state-of-the-art performance**  with substantially **lower cost** through training on **native resolution** images.
 
-**LLaVA-OneVision-1.5** introduces a novel family of **fully open-source** Large Multimodal Models (LMMs) that achieves **state-of-the-art performance**  with substantially **lower cost** through training on **native resolution** images.
+- **Superior Performance**
+A family of fully open-source large multimodal models demonstrating 
+    - Superior performance across multiple multimodal benchmarks
+    - outperforming **Qwen2.5-VL** in most evaluation tasks.
 
-1. **Superior Performance**
-A family of fully open-source large multimodal models demonstrating **superior performance** across multiple multimodal benchmarks, **outperforming Qwen2.5-VL** in most evaluation tasks.
+- **High-Quality Data at Scale**
+Meticulously curated **pre-training and SFT data** with rigorous filtering and quality control, achieving **superior data efficiency** with only **64B tokens**.
+    - Concept-balanced, highly diverse, high-quality caption data
+    - Comprehensive instruction fine-tuning data covering a wide range of tasks
 
-2. **High-Quality Data at Scale**
-Meticulously curated **mid-training and SFT data** with rigorous filtering and quality control.
-- Concept-balanced, highly diverse, high-quality caption data
-- Comprehensive instruction fine-tuning data covering a wide range of tasks
+- **Ultra-Efficient Training Framework** Complete end-to-end training framework designed for maximum efficiency:
+    - $16000 total budget for full model training on A100 GPUs  ($0.6 per GPU/Hour)
+    - 45% HFU efficiency in 8k context length
+    - Built on **MegatronLM** with support for **MoE**, **FP8**, and **long sequence parallelization**
+    - Optimized codebase for cost-effective scaling
 
-3. **Ultra-Efficient Training Framework**
-Complete end-to-end training framework designed for maximum efficiency:
-- **$16K total budget** for full model training
-- **45% HFU efficiency** on A100 GPUs ($0.6 per GPU/Hour)
-- Built on **MegatronLM** with support for **MoE**, **FP8**, and **long sequence parallelization**
-- Optimized codebase for cost-effective scaling
 
-4. **Fully Open Framework** for community access and reproducibility:
-- ✅ High-quality mid-training & SFT data
-- ✅ Complete training framework & code
-- ✅ Training recipes & configurations
-- ✅ Base & instruct model checkpoints
-- ✅ Comprehensive training logs & metrics
+- **Fully Open Framework** for community access and reproducibility:
+    - High-quality pre-training & SFT data
+    - Complete training framework & code
+    - Training recipes & configurations
+    - Comprehensive training logs & metrics
+
+
+## Models
+
+| Model                    | HF Link                                                                                      | Training Log |
+|--------------------------|--------------------------------------------------------------------------------------------------------|-------------|
+| LLaVA-OV-1.5-4B-Instruct | [🤗 HF / 4B-Instruct](https://huggingface.co/lmms-lab/LLaVA-OneVision-1.5-4B-Instruct)                | Uploading…    |
+| LLaVA-OV-1.5-8B-Instruct | [🤗 HF / 8B-Instruct](https://huggingface.co/lmms-lab/LLaVA-OneVision-1.5-8B-Instruct)                | [📈 Tensorboard](https://huggingface.co/lmms-lab/LLaVA-OneVision-1.5-8B-Instruct/tensorboard) |
+
+## Datasets
+
+![Dataset Visualization](asset/dataset.jpg)
+<p align="left">
+  <strong>(a)</strong> The vocabulary coverage proportion in the LLaVA-OneVision-1.5 Mid-Training dataset before and after concept balancing.
+  <strong>(b)</strong> Distribution of data sources within the LLaVA-OneVision-1.5 Mid-Training dataset.
+  <strong>(c)</strong> Distribution of data sources within the LLaVA-OneVision-1.5 Insturct dataset.
+</p>
+
+| Description        | Link                                                                                                   | Status      |
+|--------------------|--------------------------------------------------------------------------------------------------------|-------------|
+| OV-1.5-Mid-Training-85M   | [🤗HF/85M](https://huggingface.co/datasets/lmms-lab/LLaVA-One-Vision-1.5-Mid-Training-85M) | Uploading…  |
+| OV-1.5-Instruct           | [🤗HF/Inst](https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-1.5-Insturct-Data)     | Uploading…  |
 
 ## Code
 This model is trained using a fully open-source, end-to-end training framework, with all code available at [EvolvingLMMs-Lab/LLaVA-OneVision-1.5](https://github.com/EvolvingLMMs-Lab/LLaVA-OneVision-1.5).
 
-## Dataset
-| Description | Link |
-|-------------|------|
-| Mid-training data for LLaVA-OneVision-1.5 | [🤗 Download (Uploading!)](https://huggingface.co/datasets/lmms-lab/LLaVA-One-Vision-1.5-Mid-Training-85M) |
-| SFT data for LLaVA-OneVision-1.5 | [🤗 Download (Uploading!)](https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-1.5-Insturct-Data) |
 
 ## Evaluation Results
 All evaluations were conducted using [lmms_eval](https://github.com/EvolvingLMMs-Lab/lmms-eval).