LilTii Collection A 0.6B Bengali Language Model that Outperforms Qwen. • 10 items • Updated 7 days ago • 1
LilTii Collection A 0.6B Bengali Language Model that Outperforms Qwen. • 10 items • Updated 7 days ago • 1
LilMoo Collection A 0.6-billion-parameter Hindi language models trained entirely from scratch. • 11 items • Updated 7 days ago • 2
Running Agents 5 TeenyTinyLlama-Chat 🦙 5 Chat with TeenyTinyLlama and explore its fine‑tuning examples
Tucano2 Collection An open suite of large language models (LLMs) with 0.5-3.7 billion parameters, designed to address the gap in open-source development for Portuguese. • 33 items • Updated Mar 11 • 16
view article Article LilTii: A 0.6B Bengali Language Model that Outperforms Qwen Polygl0t • Mar 5 • 3
Running on CPU Upgrade 246 The Synthetic Data Playbook: Generating Trillions of the Finest Tokens 📝 246 Explore synthetic data benchmarks via an interactive bookshelf