19uez/llama3_2_3B_128_005_5k_GRPO_full_model download history

19uez/llama3_2_3B_128_005_5k_GRPO_full_model is a 3.2B-parameter text generation model by 19uez. In the last 30 days it was downloaded 8 times (4 in the last 7 days), and 49 times in total.

It ranks #941,300 on the Hub by monthly downloads and #350,388 among text generation models.

It has 0 likes.

It is a fine-tune of 19uez/llama_3b_sft_best.

1 models build on llama3_2_3B_128_005_5k_GRPO_full_model: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 25 times in the last 30 days. See the llama3_2_3B_128_005_5k_GRPO_full_model galaxy.

Most downloaded derivatives

Open 19uez/llama3_2_3B_128_005_5k_GRPO_full_model on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.