mradermacher/Spaetzle-v63-7b-GGUF
Same weights, converted vs cstr/Spaetzle-v63-7b. 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
Same weights, converted vs cstr/Spaetzle-v63-7b. 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