razisayyed/expense-extraction-0.8B
LoRA-style vs unsloth/Qwen3.5-0.8B. 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, out_proj, q_proj, up_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Attention 42/220, Norms 0/135, Embeddings 0/5, MLP 72/127, other 0/1
1 derivatives checked
- mradermacher/expense-extraction-0.8B-GGUF: Partial fine-tune