pplx-embed-v1-4b

from sentence_transformers import SentenceTransformer

model = SentenceTransformer(
    "perplexity-ai/pplx-embed-v1-4B",
    trust_remote_code=True
)

texts = [
    "Scientists explore the universe driven by curiosity.",
    "Children learn through curious exploration.",
    "Historical discoveries began with curious questions.",
    "Animals use curiosity to adapt and survive.",
    "Philosophy examines the nature of curiosity.",
]

embeddings = model.encode(texts) # Shape: (5, 2560), quantized to int8
embeddings = model.encode(texts, quantization="binary") # Shape: (5, 2560), quantized to binary

import onnxruntime as ort
from transformers import AutoTokenizer
import numpy as np

tokenizer = AutoTokenizer.from_pretrained("perplexity-ai/pplx-embed-v1-4b", trust_remote_code=True)
session = ort.InferenceSession("onnx/model.onnx")


texts = [
    "Scientists explore the universe driven by curiosity.",
    "Children learn through curious exploration.",
    "Historical discoveries began with curious questions.",
    "Animals use curiosity to adapt and survive.",
    "Philosophy examines the nature of curiosity.",
]

tokenized = tokenizer(
    texts,
    padding=True,
    truncation=True,
    return_tensors="np"
)

onnx_inputs = {
    "input_ids": tokenized["input_ids"].astype(np.int64),
    "attention_mask": tokenized["attention_mask"].astype(np.int64),
}

# Run inference
onnx_embeddings = session.run([out.name for out in session.get_outputs()], onnx_inputs)

# ONNX produces both int8 and binary precision embeddings:
int8_embeddings = onnx_embeddings[2]
binary_embeddings = onnx_embeddings[3]
packed_embeddings = np.packbits(binary_embeddings != -1, axis=-1)

docker run -p 8080:80 ghcr.io/huggingface/text-embeddings-inference:cpu-1.9 --model-id perplexity-ai/pplx-embed-v1-4B --dtype float32