cstr/Spaetzle-v60-7b
Full fine-tune vs abideen/AlphaMonarch-dora. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
2 derivatives checked
- mradermacher/Spaetzle-v60-7b-i1-GGUF: Quantization
- featherless-ai-quants/cstr-Spaetzle-v60-7b-GGUF: Quantization