MCG-NJU/TimeLens2-2B
Partial fine-tune vs Qwen/Qwen3-VL-2B-Instruct. Partial change: 86% of the weights changed (attention, embeddings, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 1/4, Norms 107/217, MLP 100/196, Attention 112/208
1 derivatives checked
- mradermacher/TimeLens2-2B-GGUF: Same weights, converted (fewer layers)