Update README.md

README.md

@@ -13,17 +13,25 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bart_developer_keywords
 
-This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the None dataset.
+This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on a private dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8795
 
 ## Model description
 
-More information needed
+This model extracts tech terms, tools, company names and processes from texts so they can easily be aggregated. It is trained to extract tech terms, tools, languages, platforms but may be used on other texts.
 
 ## Intended uses & limitations
 
-More information needed
+Use to extract keywords from texts.
+
+Example text: "If a task raises an exception, or a worker process dies, Celery will by default lose the job. So if you happen to reboot or redeploy, any running jobs with be lost to the sands of time."
+
+Output: "Celery, Exception Handling, Worker Process, Redundant"
+
+Example text: "Spin 2.0 – open-source tool for building and running WebAssembly applications -"
+
+Output: "Spin 2.0, WebAssembly, Open Source"
 
 ## Training and evaluation data
 
@@ -31,6 +39,7 @@ More information needed
 
 ## Training procedure
 
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training: