Upload app.py with huggingface_hub

app.py

@@ -0,0 +1,69 @@
+
+import gradio as gr
+import time
+
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextGenerationPipeline
+
+MODEL_ID = "akshaynayaks9845/rml-ai-phi1_5-rml-100k"
+
+def load_pipeline():
+    try:
+        tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+        model = AutoModelForCausalLM.from_pretrained(MODEL_ID)
+        pipe = TextGenerationPipeline(model=model, tokenizer=tokenizer, device=-1)
+        return pipe
+    except Exception as e:
+        return str(e)
+
+pipe_or_err = load_pipeline()
+
+SAMPLES = [
+    "What is artificial intelligence?",
+    "Explain machine learning in one sentence.",
+    "What is quantum computing?",
+]
+
+def generate_response(prompt, max_new_tokens=128, temperature=0.2):
+    start = time.time()
+    if isinstance(pipe_or_err, str):
+        return f"Model load error: {pipe_or_err}"
+    try:
+        outputs = pipe_or_err(
+            prompt,
+            max_new_tokens=int(max_new_tokens),
+            do_sample=bool(temperature and temperature > 0),
+            temperature=float(temperature),
+            top_p=0.9,
+            repetition_penalty=1.1,
+            truncation=True,
+        )
+        text = outputs[0]["generated_text"]
+        # Return only continuation if the model echoes the prompt
+        reply = text[len(prompt):].strip() if text.startswith(prompt) else text
+        elapsed = int((time.time() - start) * 1000)
+        return f"{reply}
+
+(⏱️ {elapsed} ms)"
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+with gr.Blocks(title="RML-AI Demo") as demo:
+    gr.Markdown('''
+    # RML-AI Demo
+    Ask a question below. The model will respond in GPT-style. This is a lightweight prototype demo.
+    ''')
+    with gr.Row():
+        prompt = gr.Textbox(label="Your question", value=SAMPLES[0])
+    with gr.Row():
+        max_new = gr.Slider(32, 256, value=128, step=16, label="Max new tokens")
+        temp = gr.Slider(0.0, 1.0, value=0.2, step=0.1, label="Temperature")
+    with gr.Row():
+        btn = gr.Button("Generate")
+    output = gr.Textbox(label="Answer", lines=8)
+    with gr.Row():
+        gr.Examples(SAMPLES, inputs=prompt)
+
+    btn.click(generate_response, [prompt, max_new, temp], output)
+
+if __name__ == "__main__":
+    demo.launch()