Continue finetuning using LoRA from 0.5B up to 72B.
Mesolitica
company
AI & ML interests
We develop Multimodality, lab from Malaysia
Recent Activity
View all activity
Collections
14
models
259
mesolitica/Malaysian-gemma-3-27b-it
Updated
mesolitica/Malaysian-gemma-3-1b-it
Updated
mesolitica/Malaysian-Llama-3.2-1B-Instruct
Updated
mesolitica/Malaysian-Llama-3.2-3B-Instruct
Updated
mesolitica/Malaysian-Llama-3.1-8B-Instruct
Updated
mesolitica/Malaysian-Llama-3.2-1B-Instruct-v0.2
Updated
•
13
mesolitica/Malaysian-Llama-3.2-1B-Instruct-v0.1
Updated
•
3
mesolitica/Malaysian-Llama-3.2-3B-Instruct-v0.1
Updated
•
19
•
2
mesolitica/Malaysian-Llama-3.1-8B-Instruct-v0.1
Updated
•
5
mesolitica/Malaysian-Llama-3.2-3B-Instruct-v0.2
Updated
•
129
datasets
216
mesolitica/Malaysian-Text-Benchmark
Preview
•
Updated
•
30
mesolitica/Speech-Nonverbal-Whisper
Viewer
•
Updated
•
28.2k
•
48
mesolitica/Malaysian-STT-Whisper-Stage2
Viewer
•
Updated
•
4.46M
•
395
•
1
mesolitica/Malaysian-Emilia
Updated
•
5.38k
•
3
mesolitica/AudioSet-Audio-Instructions
Viewer
•
Updated
•
313k
•
151
mesolitica/Speech-Translation-Instructions
Viewer
•
Updated
•
312k
•
107
•
1
mesolitica/Classification-Speech-Instructions
Viewer
•
Updated
•
118k
•
58
mesolitica/tts-combine-annotated
Viewer
•
Updated
•
360k
•
63
mesolitica/Malaysian-Speech-Instructions
Viewer
•
Updated
•
469k
•
1.61k
mesolitica/Malaysian-Voice-Conversion
Viewer
•
Updated
•
6.15M
•
154