Continue finetuning Instruct model 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
13
models
268
mesolitica/Malaysian-Qwen2.5-14B-Reasoning-GRPO
Updated
•
6
•
1
mesolitica/Malaysian-Qwen2.5-1.5B-Reasoning-GRPO
Updated
mesolitica/Malaysian-Podcast-sesame-csm-1b
Updated
•
3
mesolitica/Malaysian-sesame-csm-1b
Updated
•
10
mesolitica/Malaysian-Dia-1.6B
Updated
•
811
mesolitica/Malaysian-Podcast-Dia-1.6B
Updated
•
360
mesolitica/Malaysian-Qwen2.5-1.5B-Reasoning-SFT
Updated
•
120
mesolitica/Malaysian-Qwen2.5-7B-Dialect-Reasoning-GRPO
Updated
•
50
•
3
mesolitica/Malaysian-whisper-large-v3-turbo-v3
Updated
•
3.39k
•
5
mesolitica/Malaysian-Qwen3-14B
Updated
•
3
datasets
198
mesolitica/Speaker-Diarization-Instructions
Viewer
•
Updated
•
94.5k
•
19
mesolitica/Transcription-Instructions
Viewer
•
Updated
•
838k
•
6
mesolitica/Animal-Sound-Instructions
Viewer
•
Updated
•
28.3k
•
28
mesolitica/Malaysian-Multiturn-Chat-Assistant
Viewer
•
Updated
•
102k
•
32
mesolitica/CoVoST2-Instructions
Viewer
•
Updated
•
1.06M
•
28
mesolitica/Malaysian-Speech-Description-Timestamp-Instructions
Viewer
•
Updated
•
445k
•
46
mesolitica/Malaysian-STT-Whisper-Stage2
Viewer
•
Updated
•
1.85M
•
344
•
1
mesolitica/Malaysian-STT-Whisper
Viewer
•
Updated
•
11.9M
•
345
•
2
mesolitica/Malaysian-Emilia-Audio-Tokens
Viewer
•
Updated
•
359k
•
212
mesolitica/Malaysian-TTS-v2
Updated
•
27