Instructions to use reasonir/ReasonIR-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use reasonir/ReasonIR-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="reasonir/ReasonIR-8B", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("reasonir/ReasonIR-8B", trust_remote_code=True) model = AutoModel.from_pretrained("reasonir/ReasonIR-8B", trust_remote_code=True) - sentence-transformers
How to use reasonir/ReasonIR-8B with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("reasonir/ReasonIR-8B", trust_remote_code=True) 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
Add pipeline tag and library name
This PR adds the pipeline_tag and library_name to the model card metadata, improving discoverability and clarity. The pipeline_tag is set to text-ranking based on the model's description and usage examples. The library_name is set to transformers due to the provided code examples using the transformers library.
I feel like pipeline_tag: feature-extraction might be stronger, text-ranking is mostly used for rerankers :)
Thanks, updated. Btw @qiaoruiyt would be great to move the model and dataset to the Meta org: https://huggingface.co/facebook
Thank you for the help @nielsr @tomaarsen ! Regarding the organization transfer, we are looking into it. We can keep it this way for now to ensure the consistency with the paper and codebase that people are already using.