larped/SmolLM2-1.7B-Instruct-obliteratus
Partial fine-tune vs HuggingFaceTB/SmolLM2-1.7B-Instruct. Partial change: 22% of the weights changed (attention, embeddings, mlp), in 4 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 0/49, MLP 12/72, Attention 16/96
2 derivatives checked
- mradermacher/SmolLM2-1.7B-Instruct-obliteratus-i1-GGUF: Quantization
- mradermacher/SmolLM2-1.7B-Instruct-obliteratus-GGUF: Same weights, converted