Llama3.2-1B-DPO-LoRA

Description

Llama3.2-1B-DPO-LoRA is an open-weight text-generation model with roughly 1B parameters published by RantiRepo on the Hugging Face Hub. It has 240 downloads. Runs with transformers.

Categories

• Productivity

Tags

• llama
• text-generation
• gpt2
• dpo
• lora
• preference-optimization
• conversational
• id

Capabilities

• Text generation
• Conversational
• Library: transformers
• 1B parameters