kwisschen/qwen3-embedding-0.6b-patent-oa-rejections
LoRA-style vs Qwen/Qwen3-Embedding-0.6B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 112/112