automerger/NeuralExperiment26-7B
Full fine-tune vs Kukedlc/Neural-Krishna-Multiverse-7b-v3. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 19/65, MLP 93/96, Attention 124/128, lm_head 1/1
3 derivatives checked
- MaziyarPanahi/NeuralExperiment26-7B-GGUF: Quantization
- MaziyarPanahi/T3qm7xNeuralsirkrishna_NeuralExperiment26: Full fine-tune
- MaziyarPanahi/YamshadowStrangemerges_32_NeuralExperiment26: Full fine-tune