badr7 commited on
Commit
b3693ff
·
verified ·
1 Parent(s): 19e20e0

benchmark card on the page

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -6,6 +6,9 @@ tags: [tau2-bench, agents, tool-use, customer-support, lora]
6
  ---
7
  # rapidchat ⚡
8
 
 
 
 
9
  **a 9B that handles airline customer support on [τ²-bench](https://github.com/sierra-research/tau2-bench). built in about a day and a half. ngl, that's the point.**
10
 
11
  the full training + practice data is open too: **[rapidchat-data](https://huggingface.co/datasets/badr7/rapidchat-data)** 📦
 
6
  ---
7
  # rapidchat ⚡
8
 
9
+ ![rapidchat vs the frontier on τ²-bench airline](benchmark_card.png)
10
+
11
+
12
  **a 9B that handles airline customer support on [τ²-bench](https://github.com/sierra-research/tau2-bench). built in about a day and a half. ngl, that's the point.**
13
 
14
  the full training + practice data is open too: **[rapidchat-data](https://huggingface.co/datasets/badr7/rapidchat-data)** 📦