mesolitica/Malaysian-Qwen2.5-1.5B-Reasoning-SFT
2B
•
Updated
•
135
Malaysian Reasoning
Full parameter post training using SFT warmup and GRPO.
-
-
mesolitica/Malaysian-Qwen2.5-1.5B-Reasoning-GRPO
2B • Updated • 54 -
mesolitica/Malaysian-Qwen2.5-7B-Reasoning-SFT
8B • Updated • 1.84k • 1 -
mesolitica/Malaysian-Qwen2.5-7B-Dialect-Reasoning-GRPO
8B • Updated • 77 • 3 -
mesolitica/Malaysian-Qwen2.5-14B-Reasoning-SFT
15B • Updated • 1.87k -
mesolitica/Malaysian-Qwen2.5-14B-Reasoning-GRPO
15B • Updated • 63 • 1