Magpie-Align/MagpieLM-8B-SFT-v0.1
Full fine-tune vs meta-llama/Llama-3.1-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 1/1
5 derivatives checked
- mradermacher/MagpieLM-8B-SFT-v0.1-i1-GGUF: Quantization
- QuantFactory/MagpieLM-8B-Chat-v0.1-GGUF: Full fine-tune
- mradermacher/MagpieLM-8B-SFT-v0.1-GGUF: Same weights, converted
- tensorblock/MagpieLM-8B-SFT-v0.1-GGUF: Quantization
- Magpie-Align/MagpieLM-8B-Chat-v0.1: Full fine-tune