Goekdeniz-Guelmez/Josiefied-Qwen3-1.7B-abliterated-v1-gguf

Same weights, converted vs Goekdeniz-Guelmez/Josiefied-Qwen3-1.7B-abliterated-v1. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse