DidulaThavishaPro/exp_16_1_0grpo_checkpoint_660_16bit_vllm download history

DidulaThavishaPro/exp_16_1_0grpo_checkpoint_660_16bit_vllm is a 7.6B-parameter text generation model by DidulaThavishaPro. In the last 30 days it was downloaded 15 times (5 in the last 7 days), and 99 times in total.

It ranks #535,247 on the Hub by monthly downloads and #180,419 among text generation models.

It has 0 likes.

It is a fine-tune of DidulaThavishaPro/exp_11_0_sft_16bit_vllm.

Open DidulaThavishaPro/exp_16_1_0grpo_checkpoint_660_16bit_vllm on Hugging Face