Modelpublic

seslami-pplx/pplx-embed-context-v1.4-4B

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

1likes7.4kdownloads

Model Card

pplx-embed-context-v1.4-4B

Contextual sentence-embedding model. Same architecture and loading code as the `v1.3-4B` release — drop-in replacement.

Targets the same three failure modes as prior versions: paraphrase resolution, lexical-distractor pull, and glossary co-retrieval.

Usage

<details> <summary>Using Transformers</summary>

python

from transformers import AutoModel

model_ctx = AutoModel.from_pretrained(
    "seslami-pplx/pplx-embed-context-v1.4-4B",
    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)

</details>