ewin-reg/WeMM-Embedding-2B-GGUF
Quantization vs tencent/WeMM-Embedding-2B. ewin-reg/WeMM-Embedding-2B-GGUF is a GGUF quantization (Q8_0) of the same weights: 61 tensors match exactly and 98 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24