mesolitica/Malaysian-Qwen2.5-14B-Reasoning-GRPO download history
mesolitica/Malaysian-Qwen2.5-14B-Reasoning-GRPO is a 14.8B-parameter model model by mesolitica. In the last 30 days it was downloaded 32 times (10 in the last 7 days), and 238 times in total.
It ranks #305,970 on the Hub by monthly downloads.
It has 1 likes.
It is a fine-tune of mesolitica/Malaysian-Qwen2.5-14B-Reasoning-SFT.
1 models build on Malaysian-Qwen2.5-14B-Reasoning-GRPO: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 354 times in the last 30 days. See the Malaysian-Qwen2.5-14B-Reasoning-GRPO galaxy.
Most downloaded derivatives
- mradermacher/Malaysian-Qwen2.5-14B-Reasoning-GRPO-GGUF (quantized), 322 downloads in 30 days
Open mesolitica/Malaysian-Qwen2.5-14B-Reasoning-GRPO on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.