backyardai/InfinityKuno-2x7B-GGUF
Same weights, converted vs R136a1/InfinityKuno-2x7B. Same weights stored in another dtype (BF16 → F16/F32), plus 192 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, Attention 0/128, other 0/32
Same weights, converted vs R136a1/InfinityKuno-2x7B. Same weights stored in another dtype (BF16 → F16/F32), plus 192 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, Attention 0/128, other 0/32