Ouro-1.4B-Thinking-depth-GRPO

Description

Ouro-1.4B-Thinking-depth-GRPO is an open-weight text-generation model with roughly 1.4B parameters published by omar81939 on the Hugging Face Hub. It has 283 downloads. Runs with transformers.

Categories

• Coding
• Research
• Productivity

Tags

• ouro
• text-generation
• looped-language-model
• recurrent-depth
• reinforcement-learning
• grpo
• math
• conversational

Capabilities

• Text generation
• Conversational
• Library: transformers
• 1.4B parameters