automerger/Inex12Neural-7B

Full fine-tune vs Kukedlc/Neural-Krishna-Multiverse-7b-v3. Fine-tune: 94% of the weights changed, across 31 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 26/65, MLP 90/96, Attention 120/128, lm_head 1/1

3 derivatives checked

• MaziyarPanahi/Inex12Neural-7B-GGUF: Quantization
• mradermacher/Inex12Neural-7B-GGUF: Quantization
• MaziyarPanahi/NeuralsirkrishnaShadow_Inex12Neural: Full fine-tune

On the Hub · Downloads on Model Pulse