Update README.md

README.md

@@ -4,9 +4,14 @@ tags:
 model-index:
 - name: asturGPT
   results: []
-pipeline_tag: conversational
+widget:
+- text: "L'asturianu ye un"
+- text: "Juan ye"
+- text: "Tolos miércoles voi al mercáu y"
+- text: "Gústenme los: "
+- text: "El mio sieglu favoritu ye"
 datasets:
-  - sam-chami/asturian
+- sam-chami/asturian
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 # asturGPT
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+THIS MODEL IS A WIP
+This model is an Asturian GPT-2 model trained from scratch with the [sam-chami/asturian](https://huggingface.co/datasets/sam-chami/asturian) dataset.
 
 ## Model description