AQ-MedAI/Diver-Retriever-4B-1020

Full fine-tune vs Qwen/Qwen3-Embedding-4B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 123/145, MLP 108/108, Attention 144/144

1 derivatives checked

• mradermacher/Diver-Retriever-4B-1020-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse