NexesMess/Llama_3.x_70b_Doppelectra_v2

Full fine-tune vs Steelskull/L3.3-Electra-R1-70b. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

Tensors changed: Norms 161/161, MLP 240/240, Attention 319/320

1 derivatives checked

• mradermacher/Llama_3.x_70b_Doppelectra_v2-GGUF: Quantization

On the Hub · Downloads on Model Pulse