luckeciano/Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabelNormAdv download history

luckeciano/Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabelNormAdv is a 7.6B-parameter text generation model by luckeciano. In the last 30 days it was downloaded 27 times (9 in the last 7 days), and 2,206 times in total.

It ranks #334,611 on the Hub by monthly downloads and #93,620 among text generation models.

It has 0 likes.

It is a fine-tune of Qwen/Qwen2.5-Math-7B.

1 models build on Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabelNormAdv: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 39 times in the last 30 days. See the Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabelNormAdv galaxy.

Most downloaded derivatives

• tensorblock/luckeciano_Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabelNormAdv-GGUF (quantized), 12 downloads in 30 days

Open luckeciano/Qwen-2.5-7B-RL-LACPO-BaselineNoKLNoEntropyNoSmoothSoftLabelNormAdv on Hugging Face

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