Update README.md

README.md

@@ -13,21 +13,18 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Model_1A_Clinton
 
-This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the None dataset.
+This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on a large corpus of William J. Clinton's second term discourse on terrorism.
 
-## Model description
+## To Prompt the Model
 
-More information needed
+Try entering single words or short phrases, such as "terrorism is" or "national security" or "our foreign policy should be", 
+in the dialogue box on the right hand side of this page. 
+Then click on 'compute' and wait for the results. The model will take a few seconds to load on your first prompt.
 
 ## Intended uses & limitations
 
-More information needed
+This model is intended as an experiment on the utility of LLMs for discourse analysis on a specific corpus of political rhetoric.
 
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
 
 ### Training hyperparameters
 
@@ -40,10 +37,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 5.0
 
-### Training results
-
-
-
 ### Framework versions
 
 - Transformers 4.35.2