lmg-anon/vntl-gemma2-27b-hf
LoRA-style vs google/gemma-2-27b. 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 46 of 46 layers; norms, biases and embeddings are untouched.
Tensors changed: Attention 184/184, Norms 0/185, MLP 138/138
2 derivatives checked
- mradermacher/vntl-gemma2-27b-hf-i1-GGUF: Quantization
- mradermacher/vntl-gemma2-27b-hf-GGUF: Quantization