darkc0de/XortronCriminalComputingConfig
Partial fine-tune vs TroyDoesAI/BlackSheep-24B. Partial change: 88% of the weights changed (attention, mlp, norms), in 40 of 40 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 1/81, MLP 112/120, Attention 154/160
4 derivatives checked
- mradermacher/XortronCriminalComputingConfig-i1-GGUF: Quantization
- darkc0de/XortronCriminalComputingConfig-i1-GGUF: Quantization
- mradermacher/XortronCriminalComputingConfig-GGUF: Quantization
- piconanduinopi/XortronCriminalComputingConfig-i1-GGUF: Quantization
5 other repos hold byte-for-byte identical weight files.