automerger/ShadowCalme-7B

Full fine-tune vs CorticalStack/shadow-clown-7B-dare. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 93/96, Attention 124/128, Norms 65/65, Embeddings 1/1, lm_head 1/1

2 derivatives checked

• MaziyarPanahi/ShadowCalme-7B-GGUF: Quantization
• mradermacher/ShadowCalme-7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse