Genghan

sft-deepseek-coder-33b-instruct_GRPO_nki_pure_0921_cluster4

Genghan/sft-deepseek-coder-33b-instruct_GRPO_nki_pure_0921_cluster4

sft-deepseek-coder-33b-instruct_GRPO_nki_pure_0921_cluster4 is a machine learning model from Genghan. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

RL+SFT with kernels generated by AccelOpt+NKIBench. Paper