Update README.md

README.md

@@ -27,18 +27,47 @@ This model is a fine-tuned version of [unsloth/Phi-3-mini-4k-instruct-bnb-4bit](
 
 ## 🧠 How to Use
 
-```python
 from unsloth import FastLanguageModel
+from transformers import AutoTokenizer
+import torch
+import gradio as gr
 
+# 🔃 Load model and tokenizer from Hugging Face
 model, tokenizer = FastLanguageModel.from_pretrained(
-    "sreebhargav/finetuned_phi3-cli",  
+    model_name="sreebhargav/finetuned-phi3-cli",  # Replace with your HF model path
     max_seq_length=2048,
     load_in_4bit=True,
     device_map="auto"
 )
 FastLanguageModel.for_inference(model)
 
-messages = [{"role": "user", "content": "How do I extract a .tar.gz file?"}]
-inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
-outputs = model.generate(input_ids=inputs, max_new_tokens=256)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+# 🔍 CLI Assistant function
+def cli_assistant(prompt):
+    messages = [{"role": "user", "content": prompt}]
+    inputs = tokenizer.apply_chat_template(
+        messages,
+        return_tensors="pt",
+        tokenize=True,
+        add_generation_prompt=True
+    ).to(model.device)
+
+    outputs = model.generate(
+        input_ids=inputs,
+        max_new_tokens=256,
+        temperature=0.7,
+        top_p=0.9,
+        do_sample=True,
+        eos_token_id=tokenizer.eos_token_id
+    )
+
+    decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return decoded.split("### Output:\n")[-1].strip()
+
+# 🚀 Launch Gradio demo
+gr.Interface(
+    fn=cli_assistant,
+    inputs=gr.Textbox(lines=2, placeholder="Ask about a Linux/Git/Bash command..."),
+    outputs=gr.Textbox(label="🧠 AI Response"),
+    title="🧠 CLI Assistant - Phi-3 Mini + Unsloth",
+    description="Ask your command-line questions. This model was fine-tuned with QLoRA using Unsloth."
+).launch(share=True)