BennyDaBall/Qwopus3.8-27B-Flash-NVFP4
Same weights, converted vs Jackrong/Qwopus3.8-27B-Flash. Same weights stored in another dtype (BF16 → T40/BF16), plus 63 new tensors.
Tensors changed: Norms 0/161, Embeddings 0/1, lm_head 0/1
Same weights, converted vs Jackrong/Qwopus3.8-27B-Flash. Same weights stored in another dtype (BF16 → T40/BF16), plus 63 new tensors.
Tensors changed: Norms 0/161, Embeddings 0/1, lm_head 0/1