Magpie-Align/Llama-3-8B-Magpie-Align-SFT-v0.1
Full fine-tune vs meta-llama/Meta-Llama-3-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 15/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/Llama-3-8B-Magpie-Pro-MT-SFT-v0.1-GGUF: Same weights, converted
- QuantFactory/Llama-3-8B-Magpie-Pro-MT-SFT-v0.1-GGUF: Quantization
- Magpie-Align/Llama-3-8B-Magpie-Align-v0.1: Full fine-tune