TechWolf/ConTeXT-Skill-Extraction-base
Partial fine-tune vs sentence-transformers/all-mpnet-base-v2. Partial change: 78% of the weights changed (attention, embeddings, norms, other), in 12 of 12 layers.
Tensors changed: Embeddings 2/4, Norms 48/48, Attention 97/97, other 48/50
1 derivatives checked
- abd1987/esco-context-skill-extraction: Full fine-tune
1 other repos hold byte-for-byte identical weight files.