Instructions to use Tevatron/AgentIR-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Tevatron/AgentIR-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Tevatron/AgentIR-4B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Tevatron/AgentIR-4B") model = AutoModel.from_pretrained("Tevatron/AgentIR-4B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Add metadata for library_name and pipeline_tag
Verified signatureHi! I'm Niels from the Hugging Face community team. I've opened this PR to add important metadata to your model card. By specifying `library_name: transformers` and `pipeline_tag: feature-extraction`, the model will be more discoverable on the Hub and will correctly show automated usage snippets for the community. I have also slightly improved the formatting of the model card by organizing the resource links and adding a header.8d41607
-
Update README.md
Verified signaturedc3976e -
Update README.md
Verified signature0988bc3 -
Update README.md
Verified signature7ce278e
-
Update README.md
Verified signature361252b -
Create README.md
Verified signature78586d2
-
Upload merged AgentIR-4B checkpoint
Verified signatureeb5faa1 -
initial commit
Verified signature4592fcb