bbunzeck/german-babylm-pjg-char
Text Generation
•
Updated
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
Recent Activity
authored
a paper
6 days ago
BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible
Training Data
upvoted
a
collection
12 days ago
BabyBabelLM
Organizations
bbunzeck/german-babylm-pjg-bpe
Text Generation
•
Updated
bbunzeck/german-babylm-cds-bpe
Text Generation
•
Updated
bbunzeck/german-babylm-mix-char
Text Generation
•
Updated
bbunzeck/german-babylm-mix-bpe
Text Generation
•
Updated
bbunzeck/german-babylm-cds-char
Text Generation
•
Updated
bbunzeck/lexdec-large-bpe
30M
•
Updated
•
2
bbunzeck/lexdec-medium-bpe
7.77M
•
Updated
•
2
bbunzeck/lexdec-small-bpe
2.51M
•
Updated
bbunzeck/lexdec-large-char
21.9M
•
Updated
bbunzeck/lexdec-medium-char
3.73M
•
Updated
bbunzeck/lexdec-small-char
486k
•
Updated
bbunzeck/gpt-wee-large-curriculum
Text Generation
•
Updated
•
1
bbunzeck/gpt-wee-large
Text Generation
•
Updated
•
6
bbunzeck/gpt-wee-small-curriculum
Text Generation
•
Updated
•
1
bbunzeck/gpt-wee-small
Text Generation
•
Updated
•
19
bbunzeck/gpt-wee-medium
Text Generation
•
Updated
•
4
bbunzeck/tweenie_llama
Text Generation
•
Updated
•
2
bbunzeck/weenie_llama
Text Generation
•
Updated
•
1
bbunzeck/teenie_llama
Text Generation
•
Updated
•
3
bbunzeck/baby_llama
Text Generation
•
Updated
•
2
bbunzeck/phoneme-llama-no-whitespace
Text Generation
•
15M
•
Updated
•
3
bbunzeck/grapheme-llama-no-whitespace
Text Generation
•
15.1M
•
Updated
•
6
bbunzeck/grapheme-llama
Text Generation
•
15.1M
•
Updated
•
15
•
1
bbunzeck/phoneme-llama
Text Generation
•
15M
•
Updated
•
2
bbunzeck/gpt-wee-medium-curriculum
Text Generation
•
Updated
•
1