grimjim/rogue-enchantress-32k-7B
Full fine-tune vs grimjim/cuckoo-starling-32k-7B. 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
4 derivatives checked
- mradermacher/rogue-enchantress-32k-7B-i1-GGUF: Quantization
- mradermacher/rogue-enchantress-32k-7B-GGUF: Same weights, converted
- grimjim/rogue-enchantress-32k-7B-GGUF: Quantization
- mergekit-community/EvoluzioneRed: Full fine-tune