google/gemma-3-1b-it-qat-q4_0-unquantized
Full fine-tune vs google/gemma-3-1b-it. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 156/157, MLP 78/78, Attention 104/104
6 derivatives checked
- bartowski/google_gemma-3-1b-it-qat-GGUF: Same weights, converted
- mlabonne/gemma-3-1b-it-qat-abliterated-GGUF: Full fine-tune
- unsloth/gemma-3-1b-it-qat-bnb-4bit: Quantization
- unsloth/gemma-3-1b-it-qat-unsloth-bnb-4bit: Quantization
- soob3123/amoral-gemma3-1B-v2-qat: LoRA-style
- mlabonne/gemma-3-1b-it-qat-abliterated: LoRA-style
1 other repos hold byte-for-byte identical weight files.