ddh0/Andromeda-70B
Full fine-tune vs Sao10K/Llama-3.3-70B-Vulpecula-r1. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: lm_head 1/1, Norms 161/161, Embeddings 1/1, MLP 240/240, Attention 320/320
3 derivatives checked
- bartowski/ddh0_Andromeda-70B-GGUF: Quantization
- mradermacher/Andromeda-70B-i1-GGUF: Quantization
- mradermacher/Andromeda-70B-GGUF: Quantization