Because-It-Asks/Daring-Hyst

Full fine-tune vs Kooten/DaringMaid-20B. Fine-tune: 98% of the weights changed, across 62 of 62 layers.

Tensors changed: Embeddings 1/1, Norms 125/125, MLP 183/186, Attention 244/248, lm_head 1/1

1 derivatives checked

• mradermacher/Daring-Hyst-GGUF: Quantization

On the Hub · Downloads on Model Pulse