Nitral-Archive/Kukul-Stanta-0.420-32k-7B-0.2

Full fine-tune vs ChaoticNeutrals/Eris_PrimeV4.20-Vision-32k-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

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

1 derivatives checked

• mradermacher/Kukul-Stanta-0.420-32k-7B-0.2-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse