mradermacher/Ahma-3B-Slerp-GGUF

Same weights, converted vs RASMUS/Ahma-3B-Slerp. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104

On the Hub · Downloads on Model Pulse