Building Tucano 2: Open-Source Language Models That Actually _Think_ in Portuguese
• 12
AI & ML interests
Developing foundation models for low-resource languages.
Recent Activity
View all activity
Papers
Tucano 2 Cool: Better Open Source LLMs for Portuguese
Raising Bars, Not Parameters: LilMoo Compact Language Model for Hindi
Articles
Polygl0t/gigalekh-v1
Viewer • Updated • 83.6M • 208
Polygl0t/multilingual-personas
Viewer • Updated • 52k • 87
Polygl0t/portuguese-eval-logs-olmo2-smollm3
Viewer • Updated • 203 • 297
Polygl0t/tokenizers
Viewer • Updated • 8.98M • 287
Polygl0t/portuguese-instruct-quality-qwen-annotations
Viewer • Updated • 500k • 32
Polygl0t/portuguese-toxicity-qwen-annotations
Viewer • Updated • 700k • 76
Polygl0t/portuguese-edu-qwen-annotations
Viewer • Updated • 700k • 64
Polygl0t/gigaverbo-v2-preferences
Viewer • Updated • 28.4k • 181
Polygl0t/gigaverbo-v2-sft
Viewer • Updated • 4.09M • 2.36k • 1
Polygl0t/gigaverbo-v2-synth
Viewer • Updated • 11.2M • 677
Polygl0t/gigaverbo-v2
Viewer • Updated • 375M • 4.25k • 1
Polygl0t/bengali-toxicity-qwen-annotations
Viewer • Updated • 320k • 36
Polygl0t/bengali-edu-qwen-annotations
Viewer • Updated • 320k • 80
Polygl0t/gigakriya-v1
Viewer • Updated • 41.6M • 1.48k
Polygl0t/hindi-toxicity-qwen-annotations
Viewer • Updated • 354k • 29
Polygl0t/hindi-edu-qwen-annotations
Viewer • Updated • 400k • 23
Polygl0t/LAMBADA-poly
Viewer • Updated • 30.9k • 25
Polygl0t/CALAME-PT
Viewer • Updated • 2.08k • 31
Polygl0t/IFEval-PT
Viewer • Updated • 300 • 25 • 1
Polygl0t/gsm8k-pt
Viewer • Updated • 8.76k • 183
Polygl0t/ARC-poly
Viewer • Updated • 79.6k • 695
Polygl0t/mc4-50k
Viewer • Updated • 5.4M • 417
Polygl0t/MMLU-poly
Viewer • Updated • 443k • 223 • 1
Polygl0t/Hellaswag-poly
Viewer • Updated • 275k • 65 • 1