automerger/ShadowMeliodas-7B

Full fine-tune vs AurelPx/Meliodas-7b-dare. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 96/96, Attention 128/128, Norms 64/65, Embeddings 1/1, lm_head 1/1

2 derivatives checked

• MaziyarPanahi/ShadowMeliodas-7B-GGUF: Quantization
• mradermacher/ShadowMeliodas-7B-GGUF: Quantization

On the Hub · Downloads on Model Pulse