tencent/WeMM-Embedding-9B
LoRA-style vs Qwen/Qwen3.5-9B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, in_proj_a, in_proj_b, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: MLP 96/208, Attention 152/332, Norms 0/215, Embeddings 0/3
2 derivatives checked
- TuTuCSF/WeMM-Embedding-9B-GGUF: Same weights, converted
- seamon67/WeMM-Embedding-9B-GGUF: Quantization