Upload README.md with huggingface_hub

README.md

@@ -20,17 +20,17 @@ tags:
 inference: true
 ---
 
-# Rax 4.5 - Efficient 2B Vision Language Model | Multimodal AI
+# Rax 4.5 - Efficient 2B Vision Language Model
 
-**Rax 4.5** is a state-of-the-art 2 billion parameter multimodal vision-language model optimized for production use. Process images and text together with up to 262K token context length.
+Rax 4.5 is a state-of-the-art 2 billion parameter multimodal vision-language model optimized for production use. Process images and text together with up to 262K token context length.
 
-## 🚀 Why Rax 4.5?
+## Key Features
 
-- **⚡ Fast & Efficient**: Only 2B parameters for quick inference
-- **🖼️ Vision + Text**: True multimodal understanding of images and language
-- **📏 Long Context**: 262,144 token context window for complex tasks
-- **🔧 Production Ready**: Works with vLLM, SGLang, Transformers out of the box
-- **💾 Memory Efficient**: Hybrid attention architecture reduces VRAM usage
+- Fast & Efficient: Only 2B parameters for quick inference
+- Vision + Text: True multimodal understanding of images and language
+- Long Context: 262,144 token context window for complex tasks
+- Production Ready: Works with vLLM, SGLang, Transformers out of the box
+- Memory Efficient: Hybrid attention architecture reduces VRAM usage
 
 ## Model Specifications
 
@@ -45,13 +45,13 @@ inference: true
 | **Precision** | BFloat16 |
 | **License** | Apache 2.0 |
 
-## 🔥 Key Capabilities
+## Capabilities
 
-✅ **Image Understanding** - Analyze, describe, and answer questions about images  
-✅ **Visual Question Answering** - Extract information from screenshots, documents, charts  
-✅ **Multimodal Reasoning** - Combine visual and textual information for complex tasks  
-✅ **Long Context Processing** - Handle extensive documents with visual elements  
-✅ **Production Deployment** - Optimized for real-world applications  
+- Image Understanding: Analyze, describe, and answer questions about images
+- Visual Question Answering: Extract information from screenshots, documents, charts
+- Multimodal Reasoning: Combine visual and textual information for complex tasks
+- Long Context Processing: Handle extensive documents with visual elements
+- Production Deployment: Optimized for real-world applications
 
 ## Quick Start
 
@@ -99,10 +99,9 @@ outputs = model.generate(**inputs, max_new_tokens=512)
 print(processor.decode(outputs[0], skip_special_tokens=True))
 \`\`\`
 
-### Deploy with vLLM (High Performance)
+### Deploy with vLLM
 
 \`\`\`bash
-# Start vLLM server
 vllm serve raxcore-dev/rax-3.5-chat --port 8000 --max-model-len 8192
 \`\`\`
 
@@ -124,49 +123,49 @@ response = client.chat.completions.create(
 print(response.choices[0].message.content)
 \`\`\`
 
-## 🏗️ Architecture Details
+## Architecture Details
 
-- **Hybrid Attention Mechanism**: Alternates between linear and full attention for efficiency
-- **Vision Transformer**: 24-layer encoder with 16x16 patch size, 2x2 spatial merging
-- **Optimized KV Cache**: 2 key-value heads for 75% memory reduction
-- **Multi-Resolution Position Embeddings**: Handles various image sizes and long sequences
-- **Cross-Modal Fusion**: Advanced alignment between vision and language representations
+- Hybrid Attention Mechanism: Alternates between linear and full attention for efficiency
+- Vision Transformer: 24-layer encoder with 16x16 patch size, 2x2 spatial merging
+- Optimized KV Cache: 2 key-value heads for 75% memory reduction
+- Multi-Resolution Position Embeddings: Handles various image sizes and long sequences
+- Cross-Modal Fusion: Advanced alignment between vision and language representations
 
-## 📊 Use Cases
+## Use Cases
 
-- **Document Analysis**: Extract data from invoices, receipts, forms
-- **Visual QA Systems**: Build AI that answers questions about images
-- **Content Moderation**: Analyze images with contextual understanding
-- **Educational Tools**: Explain diagrams, charts, and scientific images
-- **Accessibility**: Generate detailed image descriptions for visually impaired users
-- **E-commerce**: Product analysis and description generation
-- **Medical Imaging**: Assist with image interpretation (not diagnostic)
+- Document Analysis: Extract data from invoices, receipts, forms
+- Visual QA Systems: Build AI that answers questions about images
+- Content Moderation: Analyze images with contextual understanding
+- Educational Tools: Explain diagrams, charts, and scientific images
+- Accessibility: Generate detailed image descriptions for visually impaired users
+- E-commerce: Product analysis and description generation
+- Medical Imaging: Assist with image interpretation (not diagnostic)
 
-## ⚙️ Performance Tips
+## Performance Tips
 
-- **Temperature**: Use 0.6-0.8 for factual tasks, 0.8-1.0 for creative content
-- **Context Window**: For >32K tokens, ensure 24GB+ VRAM
-- **Batch Processing**: Process multiple images/texts together for efficiency
-- **Quantization**: Use 4-bit/8-bit quantization for lower memory footprint
-- **GPU Requirements**: Minimum 12GB VRAM (16GB recommended)
+- Temperature: Use 0.6-0.8 for factual tasks, 0.8-1.0 for creative content
+- Context Window: For >32K tokens, ensure 24GB+ VRAM
+- Batch Processing: Process multiple images/texts together for efficiency
+- Quantization: Use 4-bit/8-bit quantization for lower memory footprint
+- GPU Requirements: Minimum 12GB VRAM (16GB recommended)
 
-## 🚨 Limitations
+## Limitations
 
 - 2B parameters may struggle with highly complex reasoning vs larger models
 - Vision encoder optimized for natural images (not specialized medical/satellite imagery)
 - Long context (>100K tokens) requires significant GPU memory
 - Not fine-tuned for specific domains without additional training
 
-## 🤝 Model Comparison
+## Model Comparison
 
 | Model | Params | Context | Multimodal | Speed |
 |-------|--------|---------|------------|-------|
-| **Rax 4.5** | 2B | 262K | ✅ | ⚡⚡⚡ |
-| LLaVA 1.5 | 7B | 4K | ✅ | ⚡⚡ |
-| GPT-4V | - | 128K | ✅ | ⚡ |
-| Qwen-VL | 7B | 32K | ✅ | ⚡⚡ |
+| Rax 4.5 | 2B | 262K | Yes | Fast |
+| LLaVA 1.5 | 7B | 4K | Yes | Medium |
+| GPT-4V | - | 128K | Yes | Slow |
+| Qwen-VL | 7B | 32K | Yes | Medium |
 
-## 📖 Citation
+## Citation
 
 \`\`\`bibtex
 @misc{rax4.5,
@@ -177,15 +176,10 @@ print(response.choices[0].message.content)
 }
 \`\`\`
 
-## 📄 License
+## License
 
 Apache 2.0 - Free for commercial and research use
 
-## 🔗 Links
-
-- [Model Card](https://huggingface.co/raxcore-dev/rax-3.5-chat)
-- [Raxcore GitHub](https://github.com/raxcore-dev)
-
 ---
 
-**Keywords**: vision language model, multimodal AI, image to text, VLM, computer vision, transformers, efficient LLM, 2B parameters, long context, production AI, visual question answering, image understanding, open source AI model
+Keywords: vision language model, multimodal AI, image to text, VLM, computer vision, transformers, efficient LLM, 2B parameters, long context, production AI, visual question answering, image understanding, open source AI model