Update README.md

README.md

@@ -31,24 +31,6 @@ This is the model card for **phi-2-dialogsum**, a dialogue summarization model b
 ### Direct Use
 This model can be used directly for **dialogue summarization** tasks. For example, given a multi-turn conversation, the model will produce a succinct summary capturing the key information and context.
 
-### Downstream Use [optional]
-Could be fine-tuned or adapted for other text summarization tasks, especially conversation-like data (customer service transcripts, chat logs, interviews, etc.).
-
-### Out-of-Scope Use
-- Generating harmful or misleading content.
-- Deploying in high-stakes scenarios without proper validation (e.g., medical or legal advice).
-
-## Bias, Risks, and Limitations
-
-- **Biases:** The model may reflect biases present in the data used to train or fine-tune it.
-- **Risks:** Summaries could omit critical context or misrepresent the conversation.  
-- **Limitations:** The model’s performance may degrade on conversations with specialized jargon, code-switching, or extremely long contexts.
-
-### Recommendations
-- Always review generated summaries for accuracy.
-- Be mindful of potential biases or omissions.
-- Avoid using the model as the sole source of truth in sensitive domains.
-
 ## How to Get Started with the Model
 
 Below is a quick code snippet to load and run inference with this model:
@@ -69,6 +51,25 @@ inputs = tokenizer([input_text], max_length=512, truncation=True, return_tensors
 summary_ids = model.generate(**inputs, max_length=60, num_beams=4, early_stopping=True)
 summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
 
-print("Summary:", summary)```
+print("Summary:", summary)
+```
+
+## Training Details
+
+Training dataset (Dialogsum)[https://huggingface.co/datasets/neil-code/dialogsum-test]
+
+## Evaluation
+
+ORIGINAL MODEL:
+{'rouge1': 0.2990526195120211, 'rouge2': 0.10874019046839419, 'rougeL': 0.21186900909813286, 'rougeLsum': 0.22342464591439556}
+
+PEFT MODEL:
+{'rouge1': 0.3132817683433486, 'rouge2': 0.1070363134080079, 'rougeL': 0.23226760188839027, 'rougeLsum': 0.25947902747914586}
+
+## Absolute percentage improvement of PEFT MODEL over ORIGINAL MODEL
 
+rouge1: 1.42%
+rouge2: -0.17%
+rougeL: 2.04%
+rougeLsum: 3.61%