BennyDaBall/Qwen3.8-Uncensored-NVFP4-MTP
Same weights, converted vs JonathanColetti/Qwen3.8-27B-Uncensored. Same weights stored in another dtype (BF16 → T40/BF16), plus 63 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/161
Same weights, converted vs JonathanColetti/Qwen3.8-27B-Uncensored. Same weights stored in another dtype (BF16 → T40/BF16), plus 63 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/161