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")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Tevatron/AgentIR-4B") model = AutoModel.from_pretrained("Tevatron/AgentIR-4B") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,7 @@ When employed for end-to-end Deep Research on BrowseComp-Plus, AgentIR brings su
|
|
| 8 |
- Paper: https://arxiv.org/abs/2603.04384
|
| 9 |
- Code: https://github.com/texttron/AgentIR
|
| 10 |
- Data: https://huggingface.co/datasets/Tevatron/AgentIR-data
|
|
|
|
| 11 |
|
| 12 |
## Quick Usage
|
| 13 |
For a quick start with only minimal dependencies (`torch` and `transformers`):
|
|
|
|
| 8 |
- Paper: https://arxiv.org/abs/2603.04384
|
| 9 |
- Code: https://github.com/texttron/AgentIR
|
| 10 |
- Data: https://huggingface.co/datasets/Tevatron/AgentIR-data
|
| 11 |
+
- Project Page: https://texttron.github.io/AgentIR/
|
| 12 |
|
| 13 |
## Quick Usage
|
| 14 |
For a quick start with only minimal dependencies (`torch` and `transformers`):
|