Openintelligent123/DeepSeek-R1-Distill-Qwen-7B

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 2, 2026License:mitArchitecture:Transformer Open Weights Featherless Exclusive Cold

DeepSeek-R1-Distill-Qwen-7B is a 7.6 billion parameter distilled language model developed by DeepSeek-AI, based on the Qwen2.5-Math-7B architecture. It is fine-tuned using reasoning data generated by the larger DeepSeek-R1 model, which was developed through large-scale reinforcement learning. This model excels in reasoning, mathematical, and coding tasks, demonstrating strong performance on benchmarks like AIME 2024 and MATH-500, and supports a 32768-token context length.

Loading preview...

DeepSeek-R1-Distill-Qwen-7B Overview

DeepSeek-R1-Distill-Qwen-7B is a 7.6 billion parameter language model from DeepSeek-AI, part of their DeepSeek-R1 series. This model is a distillation of the larger DeepSeek-R1, which was developed using a novel reinforcement learning (RL) approach without initial supervised fine-tuning (SFT) to foster strong reasoning capabilities. The distillation process transfers these advanced reasoning patterns into smaller, more efficient models like this Qwen-based variant.

Key Capabilities & Features

  • Reasoning Performance: Achieves strong results in complex reasoning tasks, inheriting capabilities from the DeepSeek-R1 parent model.
  • Mathematical Proficiency: Demonstrates high performance on mathematical benchmarks such as AIME 2024 (55.5% pass@1) and MATH-500 (92.8% pass@1).
  • Code Generation: Shows competitive performance in coding challenges, with a CodeForces rating of 1189.
  • Distillation Approach: Leverages reasoning data generated by the 671B-parameter DeepSeek-R1 to fine-tune smaller, dense models, proving that complex reasoning can be effectively distilled.
  • Context Length: Supports a substantial context window of 32,768 tokens.

Usage Recommendations

  • Prompting: Avoid system prompts; integrate all instructions directly into the user prompt.
  • Reasoning Enforcement: For mathematical problems, include directives like "Please reason step by step, and put your final answer within \boxed{}" and enforce the model to start responses with "\n" to ensure thorough reasoning.
  • Temperature Setting: Recommended temperature range of 0.5-0.7 (0.6 ideal) to prevent repetitive or incoherent outputs.

Finetunes
1 models