EpistemeAI/Athena-codegemma-2-9b
LoRA-style vs EpistemeAI/EpistemeAI-codegemma-2-9b. 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
4 derivatives checked
- QuantFactory/Athena-codegemma-2-9b-v1-GGUF: Full fine-tune
- mradermacher/Athena-codegemma-2-9b-i1-GGUF: Quantization
- mradermacher/Athena-codegemma-2-9b-GGUF: Same weights, converted
- EpistemeAI/Athena-codegemma-2-9b-v1: LoRA-style