Update app.py

app.py

@@ -1,51 +1,62 @@
-#pip install huggingface_hub
-
-#export HF_TOKEN="<>"
-
-
-
+import gradio as gr
 from huggingface_hub import InferenceClient
-
-import json
-
-
-
-repo_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
-
-
-
-llm_client = InferenceClient(
-
-    model=repo_id,
-
-    timeout=120,
-
+"""
+For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+"""
+client = InferenceClient("zerostratos/test")
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+
+        response += token
+        yield response
+
+
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
 )
 
 
-
-def call_llm(inference_client: InferenceClient, prompt: str):
-
-    response = inference_client.post(
-
-        json={
-
-            "inputs": prompt,
-
-            "parameters": {"max_new_tokens": 200},
-
-            "task": "text-generation",
-
-        },
-
-    )
-
-    return json.loads(response.decode())[0]["generated_text"]
-
-
-
-
-
-response=call_llm(llm_client, "write me a crazy joke")
-
-print (response)
+if __name__ == "__main__":
+    demo.launch()