Skip to content

Intel

deepmath-v1

Based on Qwen/Qwen3-4B-Thinking-2507

Tags

  • safetensors
  • qwen3
  • math
  • reasoning
  • agent
  • qwen
  • grpo
  • reinforcement-learning
  • conversational
  • en
  • dataset:nvidia/OpenMathReasoning
  • base_model:Qwen/Qwen3-4B-Thinking-2507

Languages

en

Author
Intel
Task
text-generation
Library
transformers
Architecture
qwen3
License
apache-2.0
Base model
Qwen/Qwen3-4B-Thinking-2507
Downloads
27
Likes
12
deepmath-v1 — AI Model — AIMarketly