llama-3.2-1b-grpo-gsm8k

Description

llama-3.2-1b-grpo-gsm8k is an open-weight text-generation model with roughly 1B parameters published by bhaveshsoni0023 on the Hugging Face Hub. It has 292 downloads.

Categories

• Research
• Productivity

Tags

• llama
• grpo
• reinforcement-learning
• nemo-rl
• math
• gsm8k
• text-generation
• conversational

Capabilities

• Text generation
• Conversational
• 1B parameters