koutch/paper_smol_2.json_train_grpo_v1_train_code download history
koutch/paper_smol_2.json_train_grpo_v1_train_code is a 3.1B-parameter text generation model by koutch. In the last 30 days it was downloaded 26 times (14 in the last 7 days), and 60 times in total.
It ranks #342,391 on the Hub by monthly downloads and #96,463 among text generation models.
It has 0 likes.
It is a fine-tune of unsloth/SmolLM3-3B.
Open koutch/paper_smol_2.json_train_grpo_v1_train_code on Hugging Face