mradermacher/NSFW-flash-GGUF

Same weights, converted vs UnfilteredAI/NSFW-flash. Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/102, MLP 0/75, Attention 0/100

On the Hub · Downloads on Model Pulse