Different kinds of LMs trained with character-level tokenization
Bastian Bunzeck
bbunzeck
AI & ML interests
Cognitive and usage-based approaches to language modeling, language acquisition in humans and machines, small and efficient language models
Organizations
Collections
3
models
10
bbunzeck/grapheme-llama-no-whitespace
Updated
bbunzeck/grapheme-llama
Updated
bbunzeck/phoneme-llama-no-whitespace
Updated
bbunzeck/phoneme-llama
Updated
bbunzeck/tweenie_llama
Text Generation
•
Updated
•
2
bbunzeck/teenie_llama
Text Generation
•
Updated
•
2
bbunzeck/weenie_llama
Text Generation
•
Updated
•
2
bbunzeck/baby_llama
Text Generation
•
Updated
•
5
bbunzeck/gpt-wee-curriculum
Text Generation
•
Updated
•
4
bbunzeck/gpt-wee-regular
Text Generation
•
Updated
•
6