ViCLIP-OT
Collection
ViCLIP-OT: The First Foundation Vision-Language Model for Vietnamese Image–Text Retrieval with Optimal Transport • 3 items • Updated • 1
How to use minhnguyent546/ViCLIP-OT-checkpoints with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="minhnguyent546/ViCLIP-OT-checkpoints") # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("minhnguyent546/ViCLIP-OT-checkpoints", dtype="auto")How to use minhnguyent546/ViCLIP-OT-checkpoints with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("minhnguyent546/ViCLIP-OT-checkpoints")
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]This repository stores the official training artifacts for the ViCLIP-OT project, including model checkpoints, configs, logs, and supporting files used during experiments.
For more information, please refer to the github repository.