Update README.md

README.md

@@ -10,20 +10,47 @@ pipeline_tag: text2text-generation
 
 # T5 Chatbot
 
-A fine-tuned T5 model for conversational FAQ-style responses.
+A fine-tuned T5 model for conversational FAQ-style responses. Given a user question, the model generates a natural-language answer, making it suitable for lightweight chatbot and Q&A applications.
 
 ## Model description
-Brief explanation of what the model does and how it was trained.
+
+This model is a fine-tuned version of **[t5-small / t5-base]** (Google's T5 text-to-text transformer), adapted for conversational question-answering. It takes a user query as input and generates a relevant text response, framed as a text-to-text generation task.
 
 ## Intended uses & limitations
-What it's good for, and where it might fail.
+
+**Intended uses:**
+- FAQ-style chatbots for websites, apps, or customer support
+- Educational/demo projects exploring conversational AI with T5
+- Quick prototyping of Q&A systems
+
+**Limitations:**
+- Trained on a limited dataset, so responses may be generic or repetitive outside the training domain
+- Does not maintain multi-turn conversational context (treats each query independently)
+- English only
+- Not suitable for safety-critical or factual/medical/legal advice use cases
+- May occasionally produce inaccurate or nonsensical answers (hallucination risk common to generative models)
 
 ## Training data
-Dataset(s) used.
+
+The model was fine-tuned on a **[custom FAQ dataset / dataset name, e.g. "a collection of customer support Q&A pairs"]**. **[Add: dataset size, source, and any preprocessing steps if known.]**
 
 ## How to use
-\`\`\`python
+
+```python
 from transformers import pipeline
+
 pipe = pipeline("text2text-generation", model="UMAR798/t5-chatbot")
-pipe("your input here")
-\`\`\`
+response = pipe("What are your business hours?")
+print(response)
+```
+
+## Training procedure
+
+- Base model: **[t5-small / t5-base]**
+- Epochs: **[e.g. 3]**
+- Batch size: **[e.g. 8]**
+- Learning rate: **[e.g. 5e-5]**
+
+## Author
+
+Developed by [Muhammad Umar Farooq](https://huggingface.co/UMAR798) — [LinkedIn](https://www.linkedin.com/in/muhammad-umar-farooq-6964a430b)