gbueno86/Cathallama-70B
Full fine-tune vs Nexusflow/Athene-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1
3 derivatives checked
- mradermacher/Cathallama-70B-i1-GGUF: Quantization
- bartowski/Cathallama-70B-GGUF: Quantization
- mradermacher/Cathallama-70B-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.