mradermacher/Cygnis-Alpha-1.7B-v0.1-Instruct-GGUF
Same weights, converted vs cygnisai/Cygnis-Alpha-1.7B-v0.1-Instruct. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96
Same weights, converted vs cygnisai/Cygnis-Alpha-1.7B-v0.1-Instruct. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96