mradermacher/MFANN3bv0.17.12-GGUF

Same weights, converted vs netcat420/MFANN3bv0.17.12. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/2, Embeddings 0/1, Norms 0/66, MLP 0/128, Attention 0/256

On the Hub · Downloads on Model Pulse