Feature Extraction
sentence-transformers
Safetensors
Kernels
bidirectional_pplx_qwen3
multi-vector
custom_code
late-interaction
maxsim
pylate
text-embeddings-inference
Instructions to use perplexity-ai/pplx-embed-v1-late-0.6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use perplexity-ai/pplx-embed-v1-late-0.6b with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("perplexity-ai/pplx-embed-v1-late-0.6b", 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] - Kernels
How to use perplexity-ai/pplx-embed-v1-late-0.6b with Kernels:
# !pip install kernels from kernels import get_kernel kernel = get_kernel("perplexity-ai/pplx-embed-v1-late-0.6b") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from perplexity-ai/pplx-embed-v1-late-0.6b: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/perplexity-ai/pplx-embed-v1-late-0.6b/resolve/main/tokenizer.json
- Command line
-
hf download hf://perplexity-ai/pplx-embed-v1-late-0.6b/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/perplexity-ai/pplx-embed-v1-late-0.6b/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 46182f26f5eb7f1500aa2f8db89a2ecdc99a79f02a74f676d5cc2e1677da4e6d
- Size of remote file:
- 11.4 MB
- SHA256:
- 971941ca0ba0be4b0353fb079996a35cad610bea52dffab110551436e30b75e5
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.