Kukedlc/Neural-Krishna-Multiverse-7b-v2
Full fine-tune vs Kukedlc/Neural-Krishna-Multiverse-7b. Fine-tune: 94% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 64/65, MLP 90/96, Attention 120/128, lm_head 1/1
2 derivatives checked
- mradermacher/Neural-Krishna-Multiverse-7b-v2-i1-GGUF: Quantization
- Kukedlc/Neural-Krishna-Multiverse-7b-v3: Full fine-tune