automerger/T3qm7xNeuralsirkrishna-7B
Full fine-tune vs Kukedlc/NeuralSirKrishna-7b. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1
3 derivatives checked
- MaziyarPanahi/T3qm7xNeuralsirkrishna-7B-GGUF: Quantization
- featherless-ai-quants/automerger-T3qm7xNeuralsirkrishna-7B-GGUF: Quantization
- MaziyarPanahi/YamshadowInex12_T3qm7xNeuralsirkrishna: Full fine-tune