llama31_tulu3_8b_dpo_grpo_nonthink_intentcheck_tulu3_8b_dpo

Description

llama31_tulu3_8b_dpo_grpo_nonthink_intentcheck_tulu3_8b_dpo is an open-weight text-generation model with roughly 8B parameters published by sangyon on the Hugging Face Hub. It has 230 downloads. Runs with transformers.

Community Metrics

Categories

• Productivity

Tags

• llama
• text-generation
• grpo
• instruction-following
• intent-check
• conversational

Capabilities

• Text generation
• Conversational
• Library: transformers
• 8B parameters

Information