cygnisai/Cygnis-Alpha-1.7B-v0.1
Full fine-tune vs HuggingFaceTB/SmolLM2-1.7B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 49/49, MLP 72/72, Attention 96/96
3 derivatives checked
- mradermacher/Cygnis-Alpha-1.7B-v0.1-GGUF: Same weights, converted
- cygnisai/Cygnis-Alpha-1.7B-v0.1-GGUF: Quantization
- cygnisai/Cygnis-Alpha-1.7B-v0.1-i1-GGUF: Quantization
12 other repos hold byte-for-byte identical weight files.