dhara-250m

Description

dhara-250m is an open-weight text-generation model with roughly 250M parameters published by codelion on the Hugging Face Hub. It has 3,379 downloads. Runs with transformers.

Categories

• Coding
• Productivity

Tags

• dhara_ar
• text-generation
• diffusion-llm
• block-diffusion
• autoregressive
• self-speculation
• tri-mode
• conversational

Capabilities

• Text generation
• Conversational
• Library: transformers
• 250M parameters