Create README.md

README.md

@@ -0,0 +1,13 @@
+---
+license: mit
+---
+
+Model Description
+
+R1-Qwen-7B-R_HORIZON_Compose_1 is a reasoning model used in the paper:
+
+“R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?”
+
+This model corresponds to the Naive Training Data (n = 1) setting reported in Table 1 of the paper.
+
+The model is based on R1-distill-Qwen-7B and is trained using the naive composed reasoning training data introduced in the R-Horizon study.