Feature Extraction
Transformers
ONNX
Safetensors
multilingual
bidirectional_pplx_qwen3
sentence-similarity
conteb
contextual-embeddings
custom_code
text-embeddings-inference
Instructions to use perplexity-ai/pplx-embed-context-v1-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use perplexity-ai/pplx-embed-context-v1-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="perplexity-ai/pplx-embed-context-v1-4b", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("perplexity-ai/pplx-embed-context-v1-4b", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from perplexity-ai/pplx-embed-context-v1-4b: direct link, hf CLI and curl.
- Browser
- Download file 902 Bytes
-
https://huggingface.co/perplexity-ai/pplx-embed-context-v1-4b/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://perplexity-ai/pplx-embed-context-v1-4b/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/perplexity-ai/pplx-embed-context-v1-4b/resolve/main/special_tokens_map.json
902 Bytes
| { | |
| "additional_special_tokens": [ | |
| "<|im_start|>", | |
| "<|im_end|>", | |
| "<|object_ref_start|>", | |
| "<|object_ref_end|>", | |
| "<|box_start|>", | |
| "<|box_end|>", | |
| "<|quad_start|>", | |
| "<|quad_end|>", | |
| "<|vision_start|>", | |
| "<|vision_end|>", | |
| "<|vision_pad|>", | |
| "<|image_pad|>", | |
| "<|video_pad|>" | |
| ], | |
| "eos_token": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "mask_token": { | |
| "content": "â½Ĺ", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "sep_token": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |