blockblockblock/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-exl3-5.0bpw

Same weights, converted vs huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated. Same weights stored in another dtype (BF16 → I16/BF16), plus 123884 new tensors.

Tensors changed: Embeddings 0/4, MLP 0/192, Norms 0/241, Attention 0/258

On the Hub · Downloads on Model Pulse