Update README.md

README.md

@@ -1,3 +1,21 @@
----
-license: mit
----
+---
+license: mit
+datasets:
+- xlangai/BRIGHT
+language:
+- en
+base_model:
+- meta-llama/Llama-3.1-8B
+---
+### Model Summary
+ReasonIR-8B is the first retriever specifically trained for general reasoning tasks, achieving the state-of-the-art retrieval performance 
+on BRIGHT (reasoning-intensive retrieval). 
+When employed for retrieval-augmented generation (RAG), ReasonIR-8B also brings substantial gains on MMLU and GPQA.
+
+- Repository:
+- Paper:
+
+### Usage
+Make sure to install `transformers>=4.47.0`. 
+
+### Citation