ddh0/MiquSuperdark-70B-v1
Full fine-tune vs 152334H/miqu-1-70b-sf. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 128/161, MLP 240/240, Attention 320/320, lm_head 1/1
1 derivatives checked
- mradermacher/MiquSuperdark-70B-v1-GGUF: Quantization