ABX-AI/Spicy-Laymonade-7B
Full fine-tune vs ABX-AI/Laymonade-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 96/96, Attention 128/128, Norms 46/65, Embeddings 1/1, lm_head 1/1
3 derivatives checked
- mradermacher/Spicy-Laymonade-7B-i1-GGUF: Quantization
- mradermacher/Spicy-Lemonade-7B-GGUF: Quantization
- mradermacher/Spicy-Laymonade-7B-GGUF: Same weights, converted