VertexAGI/amethyst-1-mini
Full fine-tune (fewer layers) vs google/gemma-3-4b-it. VertexAGI/amethyst-1-mini matches part of google/gemma-3-4b-it (444 of its 883 tensors; the rest of google/gemma-3-4b-it has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 34 of 34 layers.
Tensors changed: Embeddings 1/1, Norms 200/205, MLP 102/102, Attention 136/136
2 derivatives checked
- mradermacher/amethyst-1-mini-i1-GGUF: Quantization
- mradermacher/amethyst-1-mini-GGUF: Same weights, converted