Shaik1903/ThinkLess-2B-SFT

Partial fine-tune vs Qwen/Qwen3.5-2B. Partial change: 83% of the weights changed (attention, embeddings, mlp, norms), in 24 of 24 layers.

Tensors changed: Attention 133/268, Norms 67/183, Embeddings 1/5, MLP 72/175, other 0/1

1 derivatives checked

• mradermacher/ThinkLess-2B-SFT-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse