latam-gpt/Llama-3.1-70B-LatamGPT-SFT-1.0
Full fine-tune vs meta-llama/Llama-3.1-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 148/161, MLP 240/240, Attention 320/320, lm_head 1/1
1 derivatives checked
- jairo/Llama-3.1-70B-LatamGPT-SFT-1.0-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.