pplx-embed-context-v1.3-4B (private preview)
Contextual sentence-embedding model. Same architecture and loading code as the
v1.2-4B
release — drop-in replacement.
Targets the same three failure modes as prior versions: paraphrase resolution, lexical-distractor pull, and glossary co-retrieval.
Usage
Using Transformers
from transformers import AutoModel
model_ctx = AutoModel.from_pretrained(
"seslami-pplx/pplx-embed-context-v1.3-4B",
trust_remote_code=True
)
doc_chunks = [
[
"Curiosity begins in childhood with endless questions about the world.",
"As we grow, curiosity drives us to explore new ideas.",
"Scientific breakthroughs often start with a curious question."
],
[
"The curiosity rover explores Mars searching for ancient life.",
"Each discovery on Mars sparks new questions about the universe."
]
]
# Returns list of numpy arrays (one per document)
# embeddings[0].shape = (3, 2560), embeddings[1].shape = (2, 2560)
embeddings = model_ctx.encode(doc_chunks)