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
•
198
•
1
mesolitica/nanot5-small-malaysian-translation-v2
Translation
•
Updated
•
494
•
1
mesolitica/nanot5-base-malaysian-translation-v2
Translation
•
Updated
•
65
•
1
mesolitica/Malaysian-F5-TTS-v2
Updated
mesolitica/Malaysian-F5-TTS
Updated
mesolitica/malaysian-whisper-small-v2
Updated
•
146
mesolitica/Llama-3.2-1B-Malaysian-Reasoning
Updated
•
87
mesolitica/malaysian-Llama-3.2-1B-Instruct
Updated
•
90
mesolitica/Llama-3.2-3B-Malaysian-Reasoning
Updated
•
104
mesolitica/malaysian-Llama-3.2-3B-Instruct
Updated
•
1.37k
•
2
datasets
209
mesolitica/TTS
Viewer
•
Updated
•
646k
•
148
mesolitica/pseudolabel-malaysian-youtube-whisper-large-v3-timestamp
Preview
•
Updated
•
299
mesolitica/pseudolabel-science-large-v3-timestamp
Updated
•
12
mesolitica/Malaysian-Voice-Conversion
Viewer
•
Updated
•
3.74M
•
112
mesolitica/Malaysian-SFT
Preview
•
Updated
•
303
mesolitica/Extra-Emilia
Updated
•
148
mesolitica/Malaysian-STT-Whisper
Updated
•
1.89k
•
2
mesolitica/Malaysian-Emilia
Updated
•
459
mesolitica/pseudolabel-tamil-large-v3-timestamp
Updated
•
92
mesolitica/pseudolabel-mandarin-large-v3-timestamp
Updated
•
138