allura-org/G2-9B-Sugarquill-v0
Same weights, repacked vs UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/169, MLP 0/126, Attention 0/168
4 derivatives checked
- bartowski/G2-9B-Sugarquill-v0-GGUF: Same weights, converted
- mradermacher/G2-9B-Sugarquill-v0-i1-GGUF: Quantization
- mradermacher/G2-9B-Sugarquill-v0-GGUF: Same weights, converted
- DevQuasar-3/allura-org.G2-9B-Sugarquill-v0-GGUF: Quantization