Kukedlc/Neural-Krishna-Multiverse-7b-v3
Full fine-tune vs Kukedlc/Neural-Krishna-Multiverse-7b-v2. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 25/65, MLP 93/96, Attention 124/128, lm_head 1/1
3 derivatives checked
- mradermacher/Neural-Krishna-Multiverse-7b-v3-GGUF: Quantization
- automerger/Inex12Neural-7B: Full fine-tune
- automerger/NeuralExperiment26-7B: Full fine-tune