OfficerChul/InfiGUI-G1-7B-Android-Control-5a

Full fine-tune vs InfiX-ai/InfiGUI-G1-7B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, MLP 280/280, Norms 64/122, Attention 324/324, Embeddings 1/2

2 derivatives checked

• mradermacher/InfiGUI-G1-7B-Android-Control-GGUF: Same weights, converted (fewer layers)
• mradermacher/InfiGUI-G1-7B-Android-Control-i1-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse