Pretrain from scratch 4096 context length on 90B tokens Malaysian text, https://huggingface.co/papers/2401.14680

Mesolitica
company
AI & ML interests
We develop Multimodality Artificial Intelligence for South East Asia.
Recent Activity
View all activity
Collections
24
spaces
4
models
241

mesolitica/malay-parler-tts-mini-v1
Text2Text Generation
•
Updated
•
158
•
1

mesolitica/nanot5-small-malaysian-translation-v2
Translation
•
Updated
•
171
•
1

mesolitica/nanot5-base-malaysian-translation-v2
Translation
•
Updated
•
190
•
1

mesolitica/Malaysian-F5-TTS-v2
Updated
•
1

mesolitica/Malaysian-F5-TTS
Updated

mesolitica/Llama-3.2-1B-Malaysian-Reasoning
Updated
•
19

mesolitica/malaysian-Llama-3.2-1B-Instruct
Updated
•
58

mesolitica/Llama-3.2-3B-Malaysian-Reasoning
Updated
•
70

mesolitica/malaysian-Llama-3.2-3B-Instruct
Updated
•
81
•
2

mesolitica/malaysian-vocos-mel-24khz
Updated
•
22
datasets
206
mesolitica/pseudolabel-malaysian-youtube-whisper-large-v3-timestamp
Preview
•
Updated
•
1.07k
mesolitica/TTS
Viewer
•
Updated
•
646k
•
2.67k
mesolitica/pseudolabel-science-large-v3-timestamp
Updated
•
243
mesolitica/Malaysian-Voice-Conversion
Viewer
•
Updated
•
3.74M
•
881
mesolitica/Malaysian-SFT
Preview
•
Updated
•
1.99k
•
1
mesolitica/Extra-Emilia
Updated
•
437
mesolitica/Malaysian-STT-Whisper
Updated
•
2.17k
•
2
mesolitica/Malaysian-Emilia
Updated
•
1.52k
•
1
mesolitica/pseudolabel-tamil-large-v3-timestamp
Updated
•
431
mesolitica/pseudolabel-mandarin-large-v3-timestamp
Updated
•
361