zlab-princeton/Vero-MiMo-7B

Full fine-tune vs XiaomiMiMo/MiMo-VL-7B-SFT-2508. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 2/2, Norms 50/138, MLP 304/304, Attention 380/380, lm_head 1/1

2 derivatives checked

• mradermacher/Vero-MiMo-7B-i1-GGUF: Quantization (fewer layers)
• mradermacher/Vero-MiMo-7B-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse