Create app.py

app.py

@@ -0,0 +1,37 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-70B-Instruct")
+model = AutoModelForCausalLM.from_pretrained(
+    "meta-llama/Meta-Llama-3-70B-Instruct",
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+# Inference function
+def generate_response(prompt, max_tokens=256, temperature=0.7):
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=max_tokens,
+        temperature=temperature,
+        do_sample=True,
+        top_p=0.95,
+        eos_token_id=tokenizer.eos_token_id
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Gradio interface
+gr.Interface(
+    fn=generate_response,
+    inputs=[
+        gr.Textbox(lines=4, label="Prompt"),
+        gr.Slider(50, 1024, step=10, value=256, label="Max Tokens"),
+        gr.Slider(0.1, 1.5, step=0.1, value=0.7, label="Temperature")
+    ],
+    outputs=gr.Textbox(label="Generated Response"),
+    title="Meta LLaMA 3 70B Instruct",
+    description="Gradio demo for Meta-Llama-3-70B-Instruct"
+).launch()