reverting to init template

app.py

@@ -1,108 +1,63 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-# from transformers import AutoModelForCausalLM, AutoTokenizer
-# import spaces
 
 """
 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("BatsResearch/bonito-v1")
-# model = AutoModelForCausalLM.from_pretrained("BatsResearch/bonito-v1")
-# tokenizer = AutoTokenizer.from_pretrained("BatsResearch/bonito-v1")
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-# move to cuda
-# model.to("cuda")
 
 def respond(
-    context: str,
+    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]})
 
-    # task_type = "extractive question answering"
-    # input_text = "<|tasktype|>\n" + task_type.strip()
-    # input_text += (
-    #             "\n<|context|>\n" + context.strip() + "\n<|task|>\n"
-    # )
+    messages.append({"role": "user", "content": message})
 
-    # input_ids = tokenizer.encode(input_text, return_tensors="pt").to("cuda")
-    # outputs = model.generate(
-    #     input_ids,
-    #     max_new_tokens=max_tokens,
-    #     temperature=temperature,
-    #     do_sample=True,
-    #     top_p=top_p,
-    # )
-    # pred_start = int(input_ids.shape[-1])
-    # pred = tokenizer.decode(outputs[pred_start:], skip_special_tokens=True)
+    response = ""
 
-    # replace the context
-    pred = ""
-    return pred
-
-
-    # for token in client.text_generation(input_text, max_tokens=max_tokens, temperature=temperature, top_p=top_p, stream=True):
-    #     yield token
-
-    # 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 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
 """
-
-description = """
-This is Bonito.
-"""
-
-
-examples = [
-    "Hugging Face, Inc. is a French-American company incorporated under the Delaware General Corporation Law[1] and based in New York City that develops computation tools for building applications using machine learning. It is most notable for its transformers library built for natural language processing applications and its platform that allows users to share machine learning models and datasets and showcase their work.",
-    "In order to make your Space work with ZeroGPU you need to decorate the Python functions that actually require a GPU with @spaces.GPU \n During the time when a decorated function is invoked, the Space will be attributed a GPU, and it will release it upon completion of the function.",
-    "A spectre is haunting Europe – the spectre of communism. All the powers of old Europe have entered into a holy alliance to exorcise this spectre: Pope and Tsar, Metternich and Guizot, French Radicals and German police-spies"
-]
-
-demo = gr.Interface(
+demo = gr.ChatInterface(
     respond,
-    # inputs=[gr.Textbox(lines=5, label="Enter context here"), gr.Dropdown(["extractive question answering"], label="Task Type")],
-    inputs=gr.Textbox(lines=5, label="Enter context here"),
-    outputs=gr.Textbox(lines=20, label="Generated Instruction-Response Pairs"),
     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)",
-        # ),
+        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)",
+        ),
     ],
-    description=description,
 )
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()