DiscoverLM-70M

Description

DiscoverLM-70M is an open-weight text-generation model with roughly 70M parameters published by reaperdoesntknow on the Hugging Face Hub. It has 2,294 downloads. Runs with transformers.

Categories

• Research

Tags

• tensorboard
• moa_metric
• trl
• sft
• metric-attention
• mixture-of-attentions
• triangle-inequality
• blackhole-rope

Capabilities

• Text generation
• Library: transformers
• 70M parameters