reaperdoesntknow/Dualmind-Qwen-1.7B-Thinking

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Mar 30, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

Dualmind-Qwen-1.7B-Thinking is a 2 billion parameter Qwen3ForCausalLM model developed by Convergent Intelligence LLC: Research Division, fine-tuned using the DualMind SFT methodology on over 2.5 million tokens of Claude Opus 4.6 reasoning traces. This model specializes in extended deliberation and self-correction, absorbing the nuanced reasoning patterns of a frontier model, including backtracking and synthesis. It is built upon the DISC-refined Disctil-Qwen3-1.7B base model and is optimized for tasks requiring complex, multi-phase reasoning rather than simple pattern completion.

Loading preview...

Dualmind-Qwen-1.7B-Thinking Overview

Dualmind-Qwen-1.7B-Thinking is a 2 billion parameter model from Convergent Intelligence LLC: Research Division, specifically designed to emulate the sophisticated reasoning processes of Claude Opus 4.6. It was trained using the DualMind SFT methodology on a curated dataset of over 2.5 million tokens of Opus 4.6 reasoning traces, focusing on extended deliberation and self-correction.

Key Capabilities

  • Advanced Reasoning Emulation: Absorbs the nuanced reasoning patterns of a frontier model, including backtracking, hedging, reconsideration, and synthesis.
  • Deliberative Structure: Learns the "shape of deliberation" rather than just producing correct answers, enabling multi-phase reasoning (explore → examine → respond).
  • Strong Foundation: Built on the DISC-refined Disctil-Qwen3-1.7B base model, ensuring a robust structural foundation.
  • Extended Context: Supports a maximum context length of 40,960 tokens, allowing for long and complex reasoning chains.

Good For

  • Complex Problem Solving: Ideal for applications requiring models to navigate genuine uncertainty and perform multi-step, deliberative reasoning.
  • Cognitive Modeling: Useful for research into how smaller models can absorb and reproduce advanced cognitive processes from larger, more capable teachers.
  • Generating Detailed Explanations: Excels at producing outputs that include self-correction, re-evaluation, and synthesis, mimicking human-like thought processes.
  • Applications requiring nuanced responses: Where simple, direct answers are insufficient and a more exploratory, reflective output is desired.

Finetunes
1 models