Mawdistical/Feral-Allura-70B

Full fine-tune vs TheSkullery/Unnamed-Exp-70b-v0.7.A. Fine-tune: 99% of the weights changed, across 80 of 80 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 0/161, MLP 240/240, Attention 320/320

1 derivatives checked

• Mawdistical/Feral-Allura-70B-GGUF: Quantization

On the Hub · Downloads on Model Pulse