aifeifei798/EuroLLM-22B-Instruct-2512-FT
LoRA-style vs utter-project/EuroLLM-22B-Instruct-2512. 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 54 of 54 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/109, MLP 162/162, Attention 216/216, lm_head 0/1
2 derivatives checked
- mradermacher/EuroLLM-22B-Instruct-2512-FT-i1-GGUF: Quantization
- mradermacher/EuroLLM-22B-Instruct-2512-FT-GGUF: Quantization