mradermacher/StrangeMerges_41-7B-dare_ties-GGUF

Same weights, converted vs Gille/StrangeMerges_41-7B-dare_ties. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: MLP 0/96, Attention 0/128, Norms 0/65, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse