gdn-340m-pas-fa-layer20-10b

Description

gdn-340m-pas-fa-layer20-10b is an open-weight text-generation model with roughly 340M parameters published by startlux-models on the Hugging Face Hub. It has 199 downloads. Runs with transformers.

Categories

• Writing

Tags

• gated_deltanet
• text-generation
• fla
• gated-deltanet
• hybrid-linear-attention
• linear-attention
• massive-activations

Capabilities

• Text generation
• Library: transformers
• 340M parameters