Update README.md

README.md

@@ -25,109 +25,59 @@ It was trained using **2,000 medical instruction–response pairs** to enhance B
 | **Frameworks**         | 🤗 Transformers, PEFT, PyTorch                                                                                                                        |
 | **Hardware**           | Trained on a single NVIDIA GPU (e.g., T4 or A100)                                                                                                     |
 
----
-
-### ⚙️ Training Configuration
-
-| Parameter                 | Value                          |
-| ------------------------- | ------------------------------ |
-| `learning_rate`           | 2e-4                           |
-| `batch_size`              | 4 (with gradient accumulation) |
-| `num_train_epochs`        | 3     |
-| `optimizer`               | AdamW                          |
-
----
-
-### 🧩 Fine-tuning Workflow
-
-1. **Loaded BioGPT base model**
-
-   ```python
-   model = AutoModelForCausalLM.from_pretrained("microsoft/biogpt")
-   tokenizer = AutoTokenizer.from_pretrained("microsoft/biogpt")
-   ```
-
-2. **Applied LoRA configuration**
-
-   ```python
-   LoraConfig(
-       r=8,
-       lora_alpha=16,
-       target_modules=["c_attn", "c_proj", "q_proj", "v_proj"],
-       lora_dropout=0.1,
-       bias="none",
-       task_type="CAUSAL_LM"
-   )
-   ```
-
-3. **Trained using Hugging Face `Trainer` with EarlyStoppingCallback**
-
-   * Evaluation after each epoch
-   * Best model automatically saved
-
-4. **Merged LoRA adapter into base BioGPT**
-
-   ```python
-   merged_model = model.merge_and_unload()
-   merged_model.save_pretrained("./biogpt-lora-merged")
-   ```
-
-5. **Pushed merged model to Hugging Face Hub**
 
 ---
 
 ### 💬 Example Usage
 
 ```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
+from transformers import BioGptTokenizer, BioGptForCausalLM, set_seed
 
+# Load fine-tuned model
 model_name = "alanjoshua2005/biogpt-instruct"
-
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, dtype=torch.float16).to("cuda")
-
-prompt = """Instruction: Explain what COVID-19 is in simple terms.
-Answer:"""
-
-inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
-
-outputs = model.generate(
-    **inputs,
-    max_new_tokens=150,
-    temperature=0.7,
-    top_p=0.9,
-    do_sample=True,
-)
-
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+tokenizer = BioGptTokenizer.from_pretrained(model_name)
+model = BioGptForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16).to("cuda")
+
+# Function to get a clean model response
+def generate_response(instruction):
+    # Format the instruction properly
+    prompt = f"### Instruction: {instruction}\n### Response:"
+    
+    # Tokenize
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    
+    # Reproducibility
+    set_seed(42)
+    
+    # Generate
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            min_length=100,
+            max_length=1024,
+            temperature=0.5,   # lower = more factual, less hallucination
+            top_p=0.9,
+            do_sample=True,
+            eos_token_id=tokenizer.eos_token_id,
+        )
+    
+    # Decode and clean output
+    text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    if "### Response:" in text:
+        text = text.split("### Response:")[-1].strip()
+    if "### Instruction:" in text:
+        text = text.split("### Instruction:")[0].strip()
+    text = text.replace(instruction, "").strip()
+    
+    return text
+
+# 🧍‍♂️ User Input
+print("🧠 BioGPT Instruct — Medical Query Assistant\n")
+user_query = input("Enter your medical question or instruction:\n> ")
+
+# Get and display the response
+response = generate_response(user_query)
+print("\n🧠 Model Response:\n")
+print(response)
 ```
-
----
-
-### 📊 Example Output
-
-```
-Instruction: Explain what COVID-19 is in simple terms.
-Answer: COVID-19 is a viral disease caused by SARS-CoV-2. 
-It mainly affects the lungs and can cause fever, cough, and tiredness. 
-It spreads through droplets when an infected person coughs or sneezes.
-```
-
----
-
-### ⚠️ Disclaimer
-
-This model is **for research and educational use only**.
-It is **not a substitute for professional medical advice or diagnosis**.
-Always consult qualified medical professionals for real-world medical questions.
-
----
-
-### 🤝 Acknowledgements
-
-* [Microsoft Research](https://huggingface.co/microsoft) for releasing **BioGPT**
-* [FreedomIntelligence](https://huggingface.co/FreedomIntelligence) for the **medical reasoning dataset**
-* [Hugging Face](https://huggingface.co) and [PEFT](https://github.com/huggingface/peft) for fine-tuning utilities
-
----