LakoMoor/Silicon-Alice-7B
Full fine-tune vs LakoMoor/Silicon-Masha-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, Attention 124/128, MLP 93/96, Embeddings 1/1, lm_head 1/1
3 derivatives checked
- mradermacher/Silicon-Alice-7B-i1-GGUF: Quantization
- LakoMoor/Silicon-Alice-7B-GGUF: Quantization
- mradermacher/Silicon-Alice-7B-GGUF: Quantization