Senter Omni Model

--- license: apache-2.0 datasets: - sovthpaw/senter-omni-data language: - en base_model: - Qwen/Qwen2.5-Omni-3B pipeline_tag: any-to-any --- <div align="center">  🤘🤖 </div> **🎯 ONE MODEL, ALL MODALITIES, CHAT & EMBED** - Unlike pipeline approaches, Senter-Omni is a single 4B parameter model that truly understands and reasons across text, images, audio, and video simultaneously. **🔓 OPEN & UNCENSORED** - Apache 2.0 licensed with unrestricted responses for maximum utility. **🧠 128K CONTEXT** - Extended RoPE scaling for handling massive documents and conversations. **💾 MEMORY EFFICIENT** - 4-bit quantized model that fits on consumer GPUs while maintaining full multimodal capabilities. --- </div> ## 🚀 **Quick Start** ### **Installation** ```bash git clone https://github.com/SouthpawIN/senter-omni.git cd senter-omni pip install -r requirements.txt # Download the quantized model (instructions below) # Then run the demo: python senter_omni_demo.py ``` ### **Basic Usage** ```python from omni import OmniClient # Initialize Senter-Omni client = OmniClient() # Streaming chat response = client.chat([ {"role": "user", "content": "Hello Senter!"} ], stream=True) # Multimodal chat with image response = client.chat([ {"role": "user", "content": [ {"type": "image", "image": "photo.jpg"}, {"type": "text", "text": "What do you see?"} ]} ]) # Cross-modal embeddings embedding = client.embed("any content", modality="auto") ``` --- ## 🎭 **Multimodal Capabilities** ### **Text Understanding & Generation** - **Mathematical Reasoning**: Step-by-step problem solving - **Code Generation**: Python, JavaScript, and more - **Creative Writing**: Stories, scripts, poetry - **Technical Analysis**: Complex explanations and documentation ### **Visual Understanding** - **Image Analysis**: Detailed descriptions of visual content - **Geometric Recognition**: Shapes, colors, spatial relationships - **Creative Interpretation**: Stories inspired by images - **Technical Diagrams**: Understanding charts, graphs, schematics ### **Audio Processing** - **Sound Analysis**: Identifying audio content and patterns - **Speech Understanding**: Transcribing and interpreting spoken content - **Music Analysis**: Recognizing musical elements and genres - **Environmental Audio**: Identifying sounds from various sources ### **Cross-Modal Reason...

Source context: 0 downloads · 0 likes · Pipeline any-to-any · Repo Redvodk/senter-omni-model