mlabonne/Daredevil-8B
Full fine-tune vs Kukedlc/NeuralLLaMa-3-8b-DT-v0.1. 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
5 derivatives checked
- mlabonne/Daredevil-8B-abliterated: Abliterated
- mradermacher/Daredevil-8B-GGUF: Same weights, converted
- QuantFactory/Daredevil-8B-GGUF: Quantization
- featherless-ai-quants/mlabonne-Daredevil-8B-GGUF: Quantization
- tensorblock/Daredevil-8B-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.