gaparecido/apertus-8b-financial-reasoner-v1
LoRA-style vs swiss-ai/Apertus-8B-Instruct-2509. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 64/192, Attention 128/128, lm_head 0/1
1 derivatives checked
- mradermacher/apertus-8b-financial-reasoner-v1-GGUF: Same weights, converted