Text Retrieval
PEFT
Safetensors
sentence-transformers
English
dense-retrieval
information-retrieval
oblique-retrieval
authorship
stylometry
lora
Instructions to use DataScience-UIBK/OBLIQ-IR-3B-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use DataScience-UIBK/OBLIQ-IR-3B-LoRA with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("nvidia/llama-nv-embed-reasoning-3b") model = PeftModel.from_pretrained(base_model, "DataScience-UIBK/OBLIQ-IR-3B-LoRA") - sentence-transformers
How to use DataScience-UIBK/OBLIQ-IR-3B-LoRA with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("DataScience-UIBK/OBLIQ-IR-3B-LoRA") 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] - Notebooks
- Google Colab
- Kaggle
Update pipeline tag, link to paper page
#1
by nielsr HF Staff - opened
This PR makes the model card easier to navigate and correctly reflects what the model does.
- Updates the
pipeline_tagfromfeature-extractiontotext-retrieval, which better reflects that this repository hosts a single-vector dense retriever, and ensures the model is discoverable at https://huggingface.co/models?pipeline_tag=text-retrieval. - Adds a link to the paper page OBLIQ-IR: Training a Dense Retriever for Oblique Queries (EMNLP 2026).
Please review and merge.
abdoelsayed changed pull request status to merged