nbeerbower/Gemma2-Gutenberg-Doppel-9B
LoRA-style vs UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 42 of 42 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/169, MLP 126/126, Attention 168/168
9 derivatives checked
- bartowski/Gemma2-Gutenberg-Doppel-9B-GGUF: Same weights, converted
- QuantFactory/Gemma-2-Ataraxy-Doppel-9B-GGUF: Full fine-tune
- QuantFactory/Gemma-2-Ataraxy-v3b-9B-GGUF: Full fine-tune
- lemon07r/Gemma-2-Ataraxy-v3b-9B: Full fine-tune
- ClaudioItaly/Claustrophobia-9B: Full fine-tune
- ClaudioItaly/Stylographic-9B: Full fine-tune
- zelk12/MT1-MU-gemma-2-RGDv0.1GD-9B: Full fine-tune
- ClaudioItaly/1800-9B-V3: Full fine-tune
- lemon07r/Gemma-2-Ataraxy-Doppel-9B: Full fine-tune