tencent/WeMM-Embedding-2B
Full fine-tune vs Qwen/Qwen3.5-2B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Attention 190/264, Norms 81/177, MLP 124/172, Embeddings 1/3
8 derivatives checked
- DreamBlooms/WeMM-Embedding-2B-GGUF: Same weights, converted
- ewin-reg/WeMM-Embedding-2B-Quantized: Quantization
- ewin-reg/WeMM-Embedding-2B-GGUF: Quantization
- Weidows/WeMM-Embedding-2B-GGUF: Same weights, converted
- TuTuCSF/WeMM-Embedding-2B-GGUF: Same weights, converted
- TuTuCSF/WeMM-Embedding-GGUF-Q4_K_M: Same weights, converted
- hfadam/WeMM-Embedding-2B-MLX-4bit: Quantization
- seamon67/WeMM-Embedding-2B-GGUF: Quantization