Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: transformers
-pipeline_tag: text2text-generation
+pipeline_tag: summarization
 tags:
   - seq2seq
   - summarization
@@ -40,56 +40,42 @@ model_index:
 ## Model Details
 
 ### Model Description
-
-This model is a fine-tuned version of `google/t5-small` trained on **MIMIC-IV-BHC** clinical notes to produce simplified, patient-friendly summaries of discharge documentation.  
-It was developed as part of the *Patient-Friendly Summarization of Clinical Discharge Notes* project, which also explores a Retrieval-Augmented Generation (RAG) pipeline to improve factual grounding.
+Fine-tuned `google/t5-small` to simplify **behavioral health discharge notes** (MIMIC-IV-BHC) into patient-friendly summaries. Part of the *Patient-Friendly Summarization of Clinical Discharge Notes* project; also explored with a RAG variant for added factual grounding.
 
 - **Developed by:** Dhyan Patel & Vidit Gandhi  
-- **Funded by:** Academic course project (DS 5983 – Large Language Models)  
 - **Model type:** Encoder–decoder transformer (seq2seq)  
 - **Language(s):** English  
-- **License:** Apache 2.0  
-- **Finetuned from model:** `google/t5-small`
+- **License:** Apache-2.0  
+- **Finetuned from:** `google/t5-small`
 
 ### Model Sources
-- **Repository:** [Your Hugging Face Model Repo Link]
-- **Dataset:** [MIMIC-IV-BHC on PhysioNet](https://physionet.org/content/mimic-iv-note/)
-
----
+- **Repository:** <your model URL>
+- **Dataset:** MIMIC-IV-BHC (PhysioNet)
 
 ## Uses
 
 ### Direct Use
-- Automatically generating simplified summaries from behavioral health care discharge notes.
-- Helping patients understand complex psychiatric or psychological discharge information.
+- Generate lay summaries from behavioral health discharge notes.
 
 ### Downstream Use
-- Embedding in EHR systems for patient communication.
-- Integration with hospital discharge workflows.
-- Use in RAG pipelines to enhance factual reliability.
+- Embed in EHR/patient portals; pair with RAG to ground definitions and instructions.
 
-### Out-of-Scope Use
-- Automated diagnosis or prescribing.
-- Summarizing non-healthcare text without adaptation.
-
----
+### Out-of-Scope
+- Automated diagnosis/prescribing or any unsupervised clinical decision-making.
 
 ## Bias, Risks, and Limitations
-- May omit subtle but clinically important information when simplifying.
-- Behavioral health notes may include sensitive information; summaries must be reviewed before sharing.
-- Risks of hallucination if model is prompted with incomplete or ambiguous text.
-
----
+- May omit subtle clinical nuance; behavioral health notes can include sensitive content—human review is required.
+- Risk of hallucinations if fed incomplete context.
 
-## How to Get Started with the Model
+## How to Get Started
 ```python
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
-model_name = "your-username/patient-friendly-mimic-iv-bhc-t5-small"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+model_id = "your-username/patient-friendly-mimic-iv-bhc-t5-small"
+tok = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
 
-text = "Your clinical discharge note text here..."
-inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
-outputs = model.generate(**inputs, max_length=128)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+text = "Paste a BHC discharge note..."
+inputs = tok(text, return_tensors="pt", truncation=True, max_length=512)
+summary_ids = model.generate(**inputs, max_length=128)
+print(tok.decode(summary_ids[0], skip_special_tokens=True))