hkust-nlp/drkernel-14b-coldstart
TEXT GENERATIONConcurrency Cost:1Model Size:14BQuant:FP8Ctx Length:32kPublished:Feb 5, 2026Architecture:Transformer Cold

The hkust-nlp/drkernel-14b-coldstart is a 14 billion parameter Qwen3-based causal language model developed by hkust-nlp. This cold-start supervised fine-tuning (SFT) checkpoint is specifically designed for generating and refining structured kernel-optimization responses, aiming to replace PyTorch operators with custom Triton kernels. It serves as an initialization point for further reinforcement learning (RL) training stages, excelling as a strong SFT baseline for kernel generation tasks.

Loading preview...