Alsebay/Gemma2-9B-KuwaNovelist
LoRA-style vs lemon07r/Gemma-2-Ataraxy-v4d-9B. 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
3 derivatives checked
- mradermacher/Gemma2-9B-KuwaNovelist-i1-GGUF: Quantization
- mradermacher/Gemma2-9B-KuwaNovelist-GGUF: Same weights, converted
- mradermacher/Gemma2-9B-test-novelistwo-GGUF: Same weights, converted