Alibaba-DAMO-Academy/RynnBrain1.1-2B

Full fine-tune vs Qwen/Qwen3.5-2B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Attention 249/264, Norms 150/177, Embeddings 4/4, MLP 172/172

1 derivatives checked

• prithivMLmods/Alibaba-DAMO-Academy_RynnBrain1.1-2B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse