mradermacher/GnX-GGUF
Same weights, converted vs Edens-Gate/GnX. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/96, Attention 0/128, Norms 0/65
Same weights, converted vs Edens-Gate/GnX. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/96, Attention 0/128, Norms 0/65