rewardhack/qwen3.6-35b-a3b-hacksft-rawcot-matched-176rows-ep1
0352
model card
S2: thinking ON, raw CoT, size-matched to S1, epoch 1: full merged weights
Duplicate from gaokaiz/qwen3.6-35b-a3b-hacksft-rawcot-matched-176rows-ep1
model card
S2: thinking ON, raw CoT, size-matched to S1, epoch 1: full merged weights
Duplicate from gaokaiz/qwen3.6-35b-a3b-hacksft-rawcot-matched-176rows-ep1