Xiaojian9992024/Tau-78B-Preview
Full fine-tune vs MaziyarPanahi/calme-3.2-instruct-78b. Fine-tune: 97% of the weights changed, across 86 of 86 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 1/173, MLP 258/258, Attention 344/602
1 derivatives checked
- mradermacher/Tau-78B-Preview-GGUF: Quantization