abd1987/esco-context-skill-extraction
Full fine-tune vs TechWolf/ConTeXT-Skill-Extraction-base. Fine-tune: 99% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 4/4, Norms 48/48, Attention 97/97, other 48/50
Full fine-tune vs TechWolf/ConTeXT-Skill-Extraction-base. Fine-tune: 99% of the weights changed, across 12 of 12 layers.
Tensors changed: Embeddings 4/4, Norms 48/48, Attention 97/97, other 48/50