ntproctor/mass-academy-faq-embedder
Full fine-tune vs sentence-transformers/multi-qa-MiniLM-L6-cos-v1. Fine-tune: 99% of the weights changed, across 6 of 6 layers.
Tensors changed: Embeddings 5/5, Norms 24/24, Attention 48/48, other 24/26
1 derivatives checked
- mradermacher/mass-academy-faq-embedder-i1-GGUF: Quantization