rewardhack/qwen3.6-35b-a3b-hacksft-rawcot-matched-176rows-ep3
0405
model card
model card
S2: thinking ON, raw CoT, size-matched to S1, epoch 3: full merged weights
Duplicate from gaokaiz/qwen3.6-35b-a3b-hacksft-rawcot-matched-176rows-ep3
model card
model card
S2: thinking ON, raw CoT, size-matched to S1, epoch 3: full merged weights
Duplicate from gaokaiz/qwen3.6-35b-a3b-hacksft-rawcot-matched-176rows-ep3