Darkknight535/Contrl-Stheno-v1-8B

Full fine-tune vs Delta-Vector/Control-Nanuq-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Contrl-Stheno-v1-8B-i1-GGUF: Quantization
• mradermacher/Contrl-Stheno-v1-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse