Update README.md

README.md

@@ -1,6 +1,10 @@
 ---
 license: apache-2.0
 inference: false
+language:
+- en
+- de
+- fr
 ---
 
 # FastChat-T5 Model Card
@@ -42,4 +46,4 @@ The encoder bi-directionally encodes a question into a hidden representation. Th
 This model is fine-tuned for 3 epochs, with a max learning rate 2e-5, warmup ratio 0.03, and a cosine learning rate schedule. 
 
 ## Evaluation dataset
-A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details.
+A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details.