diff --git a/src/provider/hfgpt2.py b/src/provider/hfgpt2.py
index afde44f..e08c91e 100644
--- a/src/provider/hfgpt2.py
+++ b/src/provider/hfgpt2.py
@@ -5,7 +5,9 @@ class HuggingFaceGPT2Provider(BaseHFProvider):
     name = "GPT 2"
     slug = "hfgpt2"
     model = "gpt2"
-
+    description = "GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was trained to guess the next word in sentences."
+    languages = "English"
+    
     @property
     def require_api_key(self):
         return False
diff --git a/src/provider/hfgpt2large.py b/src/provider/hfgpt2large.py
index 34bf9d0..ae7b170 100644
--- a/src/provider/hfgpt2large.py
+++ b/src/provider/hfgpt2large.py
@@ -5,6 +5,8 @@ class HuggingFaceGPT2LargeProvider(BaseHFProvider):
     name = "GPT 2 Large"
     slug = "hfgpt2large"
     model = "gpt2-large"
+    description = "GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was trained to guess the next word in sentences."
+    languages = "English"
 
     @property
     def require_api_key(self):
diff --git a/src/provider/hfgpt2xl.py b/src/provider/hfgpt2xl.py
index e29d3e0..556661f 100644
--- a/src/provider/hfgpt2xl.py
+++ b/src/provider/hfgpt2xl.py
@@ -5,6 +5,8 @@ class HuggingFaceGPT2XLProvider(BaseHFProvider):
     name = "GPT 2 XL"
     slug = "hfgpt2"
     model = "gpt2-xl"
+    description = "GPT-2 is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was trained to guess the next word in sentences."
+    languages = "English"
 
     @property
     def require_api_key(self):