MCG-NJU/TimeLens2-4B

Partial fine-tune vs Qwen/Qwen3-VL-4B-Instruct. Partial change: 84% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/4, Norms 112/249, MLP 124/220, Attention 144/240

1 derivatives checked

• mradermacher/TimeLens2-4B-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse