HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v2
Full fine-tune vs Qwen/Qwen2-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 49/49, MLP 72/72, Attention 168/168
1 derivatives checked
- KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5: Full fine-tune