Llama-3.1-8B-SafeRLHF-RewardedSoups-baseline

Description

Llama-3.1-8B-SafeRLHF-RewardedSoups-baseline is an open-weight text-generation model with roughly 8B parameters published by promotion on the Hugging Face Hub. It has 277 downloads. Runs with transformers.

Categories

• Productivity

Tags

• llama
• text-generation
• multi-objective-alignment
• preference-optimization
• nbpo
• conversational

Capabilities

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