Magpie-Align/MagpieLM-8B-Chat-v0.1
Full fine-tune vs Magpie-Align/MagpieLM-8B-SFT-v0.1. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 11/65, MLP 96/96, Attention 128/128, lm_head 1/1
4 derivatives checked
- mradermacher/MagpieLM-8B-Chat-v0.1-i1-GGUF: Quantization
- mradermacher/MagpieLM-8B-Chat-v0.1-GGUF: Same weights, converted
- AtAndDev/Magpie-xLAM-Supernova-8B: Full fine-tune
- win10/MagpieLM-13.3B-Chat-v0.1: Partial fine-tune (fewer layers)