OfficerChul/InfiGUI-G1-3B-Android-Control-5a

Full fine-tune vs InfiX-ai/InfiGUI-G1-3B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 2/2, Norms 83/138, MLP 304/304, Attention 380/380

1 derivatives checked

• mradermacher/InfiGUI-G1-3B-Android-Control-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse