tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties
tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties is a 35.1 billion parameter language model merged using the DARE TIES method, based on Qwen/Qwen3.6-35B-A3B. It integrates capabilities from InternScience/Agents-A1 and deepreinforce-ai/Ornith-1.0-35B, specializing in advanced reasoning with a Qwen3-style reasoning parser and tool-calling. This model is optimized for complex problem-solving and agentic workflows, supporting a 32K context length.
Loading preview...
Model Overview
tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties is a 35.1 billion parameter language model created by merging InternScience/Agents-A1 and deepreinforce-ai/Ornith-1.0-35B using the DARE TIES method. It leverages Qwen/Qwen3.6-35B-A3B as its base model, combining their strengths for enhanced performance.
Key Capabilities
- Advanced Reasoning: Utilizes a Qwen3-style reasoning parser (
--reasoning-parser qwen3) to facilitate structured thought processes, enabling the model to break down and solve complex problems. - Tool-Calling: Supports Qwen3-style XML tool-calling (
--tool-call-parser qwen3_xml), making it suitable for agentic workflows where the model needs to interact with external tools or APIs. - Extended Context: Features a substantial context window of 32,768 tokens, allowing for processing and generating longer, more detailed interactions and documents.
- Multimodal Support: Configured to handle multimodal inputs, specifically images, with a limit of 4 images per prompt.
Use Cases
- Agentic AI Systems: Ideal for developing AI agents that require sophisticated reasoning and the ability to use tools to accomplish tasks.
- Complex Problem Solving: Excels in scenarios demanding structured thought and multi-step reasoning, such as scientific research, logical puzzles, or strategic planning.
- Interactive Applications: Suitable for chatbots and conversational AI that need to understand intricate user requests and provide detailed, reasoned responses.