Update README.md

README.md

@@ -3,19 +3,26 @@ library_name: transformers
 tags:
 - trl
 - dpo
+- text-generation-inference
+- poem-generation-inference
+datasets:
+- DataAnalyticsLab/Persian-Poems
+language:
+- fa
+base_model:
+- openai-community/gpt2
+pipeline_tag: text-generation
 ---
 
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
 ## Model Details
+- The model was trained using the new DPO training method using the trl.DPOTrainer and trl.DPOConfig packages. For this task, we created a dataset using the original dataset comprising positive and negative examples and by feeding them to the DPOTrainer, the model was trained. In this version, we used poems of length 1,2 and 3 Beyt shuffled randomly to train the model. The model was trained for one epoch.  
+
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+<- The model was trained using the new DPO training method using the trl.DPOTrainer and trl.DPOConfig packages. For this task, we created a dataset using the original dataset comprising positive and negative examples and by feeding them to the DPOTrainer, the model was trained. In this version, we used poems of length 1,2 and 3 Beyt shuffled randomly to train the model. The model was trained for one epoch.->
 
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.