transformer-pretraining-from-scratch

Description

transformer-pretraining-from-scratch is an open-weight text-generation model published by hari-8 on the Hugging Face Hub. It has 647 downloads. Runs with transformers.

Categories

• Coding

Tags

• decoder_transformer_scratch
• text-generation
• decoder-only
• from-scratch
• causal-lm
• custom_code
• en

Capabilities

• Text generation
• Library: transformers