Update Final Draft

app.py

@@ -0,0 +1,48 @@
+import gradio as gr
+import os
+from huggingface_hub import InferenceClient
+
+def respond(
+    message,
+    max_tokens,
+    temperature,
+    top_p
+):
+
+    client = InferenceClient(token=os.getenv('write_token'), model="meta-llama/Meta-Llama-3-70B", provider="featherless-ai")
+
+    output = client.text_generation(
+        message,
+        max_new_tokens=max_tokens,
+        stream=False,
+        temperature=temperature,
+        top_p=top_p,
+    )
+
+    return output
+
+
+demo = gr.Interface(
+    fn=respond,
+    inputs=[
+        gr.Textbox(
+            lines=10,
+            label="Input Message",
+            placeholder="Enter your message here...",
+        ),
+        gr.Slider(minimum=1, maximum=512, value=256, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0, maximum=2.0, value=1, step=0.01, label="Temperature"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
+    outputs=gr.Textbox(lines=10, label="Response")
+)
+
+
+if __name__ == "__main__":
+    demo.launch()