mradermacher/InfiGUI-G1-3B-Android-Control-GGUF

Same weights, converted (fewer layers) vs OfficerChul/InfiGUI-G1-3B-Android-Control-5a. mradermacher/InfiGUI-G1-3B-Android-Control-GGUF matches part of OfficerChul/InfiGUI-G1-3B-Android-Control-5a (434 of its 824 tensors; the rest of OfficerChul/InfiGUI-G1-3B-Android-Control-5a has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252

On the Hub · Downloads on Model Pulse