InfiX-ai/InfiGUI-G1-7B
Full fine-tune vs Qwen/Qwen2.5-VL-7B-Instruct. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/2, Norms 57/122, MLP 279/280, Attention 324/324, lm_head 1/1
4 derivatives checked
- mradermacher/InfiGUI-G1-7B-i1-GGUF: Quantization (fewer layers)
- mradermacher/InfiGUI-G1-7B-GGUF: Same weights, converted (fewer layers)
- DevQuasar/InfiX-ai.InfiGUI-G1-7B-GGUF: Same weights, converted (fewer layers)
- OfficerChul/InfiGUI-G1-7B-Android-Control-5a: Full fine-tune