CraneAILabs/swahili-gemma-1b
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 84/157, MLP 78/78, Attention 104/104
3 derivatives checked
- ThijsL202/CraneAILabs_swahili-gemma-1b-im-GGUF: Quantization
- CraneAILabs/swahili-gemma-1b-GGUF: Same weights, converted
- ThijsL202/CraneAILabs_swahili-gemma-1b-GGUF: Quantization