Bilingual LMs ( L1 {es fr de pl tr ar zh} + L2 en ) trained on Cultura-X for L1 and FineWebEdu (L2)
Suchir Salhan
suchirsalhan
AI & ML interests
Multilinguality and Cognitively-Inspired AI. Tokenization, Pretraining, Interpretability & Alignment.
Recent Activity
updated a model about 5 hours ago
Beetle-HumanScale/beetle-bilingual-l2-50-sequential-33-67-b3-humanscale-nld-eng updated a model about 6 hours ago
Beetle-FineWeb/beetle-bilingual-l2-50-simultaneous-b2-fineweb-nld-eng published a model about 6 hours ago
Beetle-FineWeb/beetle-bilingual-l2-50-simultaneous-b2-fineweb-nld-engOrganizations
models 225
suchirsalhan/B-GPT-ar-fineweb-fluent
0.1B • Updated • 2
suchirsalhan/B-GPT-zh-fineweb-fluent
0.1B • Updated • 1
suchirsalhan/B-GPT-tr-fineweb-fluent
0.1B • Updated • 1
suchirsalhan/B-GPT-zh-fineweb-advanced
0.1B • Updated • 3
suchirsalhan/B-GPT-ar-fineweb-advanced
0.1B • Updated • 2
suchirsalhan/B-GPT-tr-fineweb-advanced
0.1B • Updated • 1
suchirsalhan/B-GPT-zh-fineweb-intermediate
0.1B • Updated • 2
suchirsalhan/B-GPT-ar-fineweb-intermediate
0.1B • Updated • 2
suchirsalhan/B-GPT-tr-fineweb-intermediate
0.1B • Updated • 2
suchirsalhan/B-GPT-zh-fineweb-beginner
0.1B • Updated • 2
datasets 9
suchirsalhan/kidalign-llama-filterable
Viewer • Updated • 97.6k • 32
suchirsalhan/kidalign-llama-3.1-8B-Instruct
Updated • 2.39k
suchirsalhan/babylm-detox
Viewer • Updated • 11.6M • 45
suchirsalhan/gptbert-tokenised
Updated • 4
suchirsalhan/Phonemized-UD
Viewer • Updated • 1.19M • 39
suchirsalhan/BabyLM-Pretokenised
Viewer • Updated • 1.64M • 6
suchirsalhan/MAO-CHILDES
Viewer • Updated • 3.81M • 9
suchirsalhan/CLiMP
Preview • Updated • 34 • 1
suchirsalhan/SLING
Viewer • Updated • 40k • 33