ApsaraStackMaaS/EvoQwen2.5-VL-Retriever-3B-v1

Partial fine-tune vs vidore/colqwen2.5-base. Partial change: 74% of the weights changed (attention, mlp, other), in 36 of 36 layers.

Tensors changed: Embeddings 0/2, Norms 0/138, MLP 108/304, Attention 144/380, other 1/2

On the Hub · Downloads on Model Pulse