Add CodeLlama demo app

app.py

@@ -0,0 +1,24 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+
+model_id = "codellama/CodeLlama-7b-hf"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto"
+)
+
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+def generate_response(prompt):
+    output = pipe(prompt, max_length=512, do_sample=True, temperature=0.3)[0]['generated_text']
+    return output
+
+gr.Interface(
+    fn=generate_response,
+    inputs=gr.Textbox(lines=5, label="Your prompt"),
+    outputs=gr.Textbox(label="Code Llama response"),
+    title="Code Llama Demo",
+    description="Ask questions or request code snippets!"
+).launch()

requirements.txt

@@ -0,0 +1,3 @@
+transformers
+gradio
+accelerate