qingy2024/GRMR-V3-G4B
Full fine-tune vs unsloth/gemma-3-4b-pt. Fine-tune: 90% of the weights changed, across 34 of 34 layers.
Tensors changed: Embeddings 1/4, Norms 115/316, MLP 102/210, Attention 136/352, other 0/1
4 derivatives checked
- mradermacher/GRMR-V3-G4B-i1-GGUF: Quantization (fewer layers)
- qingy2024/GRMR-V3-G4B-GGUF: Same weights, converted (fewer layers)
- mradermacher/GRMR-V3-G4B-GGUF: Same weights, converted (fewer layers)
- icecubetr/GRMR-V3-G4B-GGUF: Same weights, converted (fewer layers)
1 other repos hold byte-for-byte identical weight files.