mesolitica/mallam-1.1B-4096
Text Generation
•
Updated
•
573
•
8
MaLLaM 🌙
Pretrain from scratch 4096 context length on 90B tokens Malaysian text, https://huggingface.co/papers/2401.14680
-
-
mesolitica/mallam-3B-4096
Text Generation • Updated • 39 • 1 -
mesolitica/mallam-5B-4096
Text Generation • Updated • 78 • 2 -
mesolitica/mallam-1.1b-20k-instructions
Text Generation • Updated • 21 • 1 -
mesolitica/mallam-1.1b-20k-instructions-v2
Text Generation • Updated • 26 -
mesolitica/mallam-3b-20k-instructions
Text Generation • Updated • 3 -
mesolitica/mallam-5b-20k-instructions
Text Generation • Updated • 13 • 1 -
mesolitica/mallam-5b-20k-instructions-v2
Text Generation • Updated • 5 • 1