DeepSeek-R1-Distill-Qwen-1.5B-SpeculativeReasoner

Description

DeepSeek-R1-Distill-Qwen-1.5B-SpeculativeReasoner is an open-weight text-generation model with roughly 1.5B parameters published by akhauriyash on the Hugging Face Hub. It has 503 downloads. Runs with transformers.

Categories

• Research
• Productivity

Tags

• qwen2
• text-generation
• generated_from_trainer
• open-r1
• trl
• sft
• conversational

Capabilities

• Text generation
• Conversational
• Library: transformers
• 1.5B parameters