nitky/Superswallow-70b-NVE

Full fine-tune vs allenai/tulu-2-dpo-70b. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1

1 derivatives checked

• mradermacher/Superswallow-70b-NVE-GGUF: Quantization

On the Hub · Downloads on Model Pulse