didula-wso2/exp_19_grpo_smooth_error_16bit_vllm download history

didula-wso2/exp_19_grpo_smooth_error_16bit_vllm is a 7.6B-parameter text generation model by didula-wso2. In the last 30 days it was downloaded 13 times (5 in the last 7 days), and 119 times in total.

It ranks #608,493 on the Hub by monthly downloads and #216,745 among text generation models.

It has 0 likes.

It is a fine-tune of didula-wso2/exp_18_1_sft_16bit_vllm.

Open didula-wso2/exp_19_grpo_smooth_error_16bit_vllm on Hugging Face