BoltMonkey/SuperNeuralDreadDevil-8b
Full fine-tune vs BoltMonkey/DreadMix. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128
4 derivatives checked
- mradermacher/SuperNeuralDreadDevil-8b-i1-GGUF: Quantization
- featherless-ai-quants/BoltMonkey-SuperNeuralDreadDevil-8b-GGUF: Quantization
- mradermacher/SuperNeuralDreadDevil-8b-GGUF: Same weights, converted
- tensorblock/SuperNeuralDreadDevil-8b-GGUF: Quantization