Sentence Similarity
Transformers
Safetensors
sentence-transformers
Chinese
utu
feature-extraction
text-embeddings-inference
custom_code
Instructions to use tencent/Youtu-Embedding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tencent/Youtu-Embedding with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("tencent/Youtu-Embedding", trust_remote_code=True, dtype="auto") - sentence-transformers
How to use tencent/Youtu-Embedding with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("tencent/Youtu-Embedding", trust_remote_code=True) sentences = [ "那是 個快樂的人", "那是 條快樂的狗", "那是 個非常幸福的人", "今天是晴天" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
need vllm support and float16 or bf16
#2
by ZhuJunling - opened
vllm support?
float16 or bf16 data type?
We uploaded the bfloat16 version of the model in the bfloat16 branch. We are currently working hard on this and expect to add vLLM support in the next 1-2 weeks.
springxchen changed discussion status to closed