Pretrain from scratch 4096 context length on 90B tokens Malaysian text, https://huggingface.co/papers/2401.14680
![](https://cdn-avatars.huggingface.co/v1/production/uploads/5e73316106936008a9ee6523/lBG9dK5tQU74OkxacXSeK.png)
Mesolitica
company
AI & ML interests
We develop Multimodality Artificial Intelligence for South East Asia.
Recent Activity
View all activity
Collections
24
spaces
4
models
240
![](https://cdn-avatars.huggingface.co/v1/production/uploads/5e73316106936008a9ee6523/lBG9dK5tQU74OkxacXSeK.png)
mesolitica/malay-parler-tts-mini-v1
Text2Text Generation
•
Updated
•
376
•
1
![](https://cdn-avatars.huggingface.co/v1/production/uploads/5e73316106936008a9ee6523/lBG9dK5tQU74OkxacXSeK.png)
mesolitica/nanot5-small-malaysian-translation-v2
Translation
•
Updated
•
324
•
1
![](https://cdn-avatars.huggingface.co/v1/production/uploads/5e73316106936008a9ee6523/lBG9dK5tQU74OkxacXSeK.png)
mesolitica/nanot5-base-malaysian-translation-v2
Translation
•
Updated
•
52
•
1
![](https://cdn-avatars.huggingface.co/v1/production/uploads/5e73316106936008a9ee6523/lBG9dK5tQU74OkxacXSeK.png)
mesolitica/Malaysian-F5-TTS-v2
Updated
![](https://cdn-avatars.huggingface.co/v1/production/uploads/5e73316106936008a9ee6523/lBG9dK5tQU74OkxacXSeK.png)
mesolitica/Malaysian-F5-TTS
Updated
![](https://cdn-avatars.huggingface.co/v1/production/uploads/5e73316106936008a9ee6523/lBG9dK5tQU74OkxacXSeK.png)
mesolitica/Llama-3.2-1B-Malaysian-Reasoning
Updated
•
76
![](https://cdn-avatars.huggingface.co/v1/production/uploads/5e73316106936008a9ee6523/lBG9dK5tQU74OkxacXSeK.png)
mesolitica/malaysian-Llama-3.2-1B-Instruct
Updated
•
91
![](https://cdn-avatars.huggingface.co/v1/production/uploads/5e73316106936008a9ee6523/lBG9dK5tQU74OkxacXSeK.png)
mesolitica/Llama-3.2-3B-Malaysian-Reasoning
Updated
•
74
![](https://cdn-avatars.huggingface.co/v1/production/uploads/5e73316106936008a9ee6523/lBG9dK5tQU74OkxacXSeK.png)
mesolitica/malaysian-Llama-3.2-3B-Instruct
Updated
•
752
•
2
![](https://cdn-avatars.huggingface.co/v1/production/uploads/5e73316106936008a9ee6523/lBG9dK5tQU74OkxacXSeK.png)
mesolitica/malaysian-vocos-mel-24khz
Updated
•
6
datasets
209
mesolitica/TTS
Viewer
•
Updated
•
646k
•
180
mesolitica/pseudolabel-malaysian-youtube-whisper-large-v3-timestamp
Preview
•
Updated
•
258
mesolitica/pseudolabel-science-large-v3-timestamp
Updated
•
19
mesolitica/Malaysian-Voice-Conversion
Viewer
•
Updated
•
3.74M
•
120
mesolitica/Malaysian-SFT
Preview
•
Updated
•
359
mesolitica/Extra-Emilia
Updated
•
157
mesolitica/Malaysian-STT-Whisper
Updated
•
2.28k
•
2
mesolitica/Malaysian-Emilia
Updated
•
462
mesolitica/pseudolabel-tamil-large-v3-timestamp
Updated
•
152
mesolitica/pseudolabel-mandarin-large-v3-timestamp
Updated
•
177