Smuggling1710/InfinToppyKuno-DARE-7bv2

Full fine-tune vs ChaoticNeutrals/Kunocchini-7b-128k-test. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

1 derivatives checked

• mradermacher/InfinToppyKuno-DARE-7bv2-GGUF: Quantization

On the Hub · Downloads on Model Pulse