Feature Extraction
sentence-transformers
Safetensors
English
Chinese
multilingual
qwen3_5
multimodal
embeddings
retrieval
quantization
mixed-precision
int8
w8a8
mrl
cross-modal
text-embeddings
image-embedding
video-embedding
custom_code
Eval Results (legacy)
8-bit precision
Instructions to use ewin-reg/WeMM-Embedding-2B-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use ewin-reg/WeMM-Embedding-2B-INT8 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("ewin-reg/WeMM-Embedding-2B-INT8", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from ewin-reg/WeMM-Embedding-2B-INT8: direct link, hf CLI and curl.
- Browser
- Download file 20 MB
-
https://huggingface.co/ewin-reg/WeMM-Embedding-2B-INT8/resolve/main/tokenizer.json
- Command line
-
hf download hf://ewin-reg/WeMM-Embedding-2B-INT8/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/ewin-reg/WeMM-Embedding-2B-INT8/resolve/main/tokenizer.json
20 MB
- Xet hash:
- de0ebff7c9772a2d3d2dec2e74f192614b356de68fd99836bc00189f082667f3
- Size of remote file:
- 20 MB
- SHA256:
- 40e444c744512f423da4c8443c47c21e22ff76056ba4e9796a81c04c13a9daf0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.