Update app.py

app.py

@@ -1,29 +1,61 @@
-!pip install transformers
-from transformers import AutoModelForCausalLM, AutoTokenizer
+import gradio as gr
+from huggingface_hub import InferenceClient
 
-device = "cuda" # or "cpu"
-model_path = "ibm-granite/granite-3b-code-base" # pick anyone from above list
+"""
+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("HuggingFaceH4/zephyr-7b-beta")
 
-tokenizer = AutoTokenizer.from_pretrained(model_path)
 
-# drop device_map if running on CPU
-model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
-model.eval()
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
 
-# change input text as desired
-input_text = "def generate():"
-# tokenize the text
-input_tokens = tokenizer(input_text, return_tensors="pt")
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
 
-# transfer tokenized inputs to the device
-for i in input_tokens:
-    input_tokens[i] = input_tokens[i].to(device)
+    messages.append({"role": "user", "content": message})
 
-# generate output tokens
-output = model.generate(**input_tokens)
-# decode output tokens into text
-output = tokenizer.batch_decode(output)
+    response = ""
 
-# loop over the batch to print, in this example the batch size is 1
-for i in output:
-    print(i)
+    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)",
+        ),
+    ],
+)
+if __name__ == "__main__":
+    demo.launch()