nbeerbower/gemma2-gutenberg-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
5 derivatives checked
- mradermacher/gemma2-gutenberg-9B-i1-GGUF: Quantization
- mradermacher/gemma2-gutenberg-9B-GGUF: Same weights, converted
- backyardai/gemma2-gutenberg-9B-GGUF: Quantization
- lemon07r/Gemma-2-Ataraxy-9B: Full fine-tune
- zelk12/MT-MU-gemma-2-Rv0.3G-9B: Full fine-tune