Feature Extraction
Transformers
Safetensors
sentence-transformers
Chinese
English
qwen3_5
image-text-to-text
multimodal-embedding
text-embedding
image-embedding
video-embedding
mrl
custom_code
Instructions to use tencent/WeMM-Embedding-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tencent/WeMM-Embedding-2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="tencent/WeMM-Embedding-2B", trust_remote_code=True)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("tencent/WeMM-Embedding-2B", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("tencent/WeMM-Embedding-2B", trust_remote_code=True, device_map="auto") - sentence-transformers
How to use tencent/WeMM-Embedding-2B with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("tencent/WeMM-Embedding-2B", 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
| { | |
| "transformer_task": "feature-extraction", | |
| "modality_config": { | |
| "text": { | |
| "method": "embedding", | |
| "method_output_name": null | |
| }, | |
| "image": { | |
| "method": "embedding", | |
| "method_output_name": null | |
| }, | |
| "video": { | |
| "method": "embedding", | |
| "method_output_name": null | |
| }, | |
| "image+text": { | |
| "method": "embedding", | |
| "method_output_name": null | |
| }, | |
| "text+video": { | |
| "method": "embedding", | |
| "method_output_name": null | |
| }, | |
| "message": { | |
| "method": "embedding", | |
| "method_output_name": null, | |
| "format": "structured" | |
| } | |
| }, | |
| "module_output_name": "sentence_embedding", | |
| "processing_kwargs": { | |
| "chat_template": { | |
| "chat_template": "sentence_transformers" | |
| } | |
| }, | |
| "unpad_inputs": false | |
| } | |