Update app.py

app.py

@@ -1,138 +1,63 @@
-import os
-from threading import Thread
-from typing import Iterator
-
 import gradio as gr
-import spaces
-import torch
-from transformers import AutoModelForCausalLM, GemmaTokenizerFast, TextIteratorStreamer
+from huggingface_hub import InferenceClient
 
-DESCRIPTION = """\
-# Gemma 2 2B IT
-Gemma 2 is Google's latest iteration of open LLMs.
-This is a demo of [`google/gemma-2-2b-it`](https://huggingface.co/google/gemma-2-2b-it), fine-tuned for instruction following.
-For more details, please check [our post](https://huggingface.co/blog/gemma2).
-👉 Looking for a larger and more powerful version? Try the 27B version in [HuggingChat](https://huggingface.co/chat/models/google/gemma-2-27b-it) and the 9B version in [this Space](https://huggingface.co/spaces/huggingface-projects/gemma-2-9b-it).
 """
+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("google/gemma-2-2b-it")
 
-MAX_MAX_NEW_TOKENS = 2048
-DEFAULT_MAX_NEW_TOKENS = 1024
-MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
-
-device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "google/gemma-2-2b-it"
-tokenizer = GemmaTokenizerFast.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
- model_id,
- device_map="auto",
- torch_dtype=torch.bfloat16,
-)
-model.config.sliding_window = 4096
-model.eval()
+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]})
 
-@spaces.GPU(duration=90)
-def generate(
- message: str,
- chat_history: list[tuple[str, str]],
- max_new_tokens: int = 1024,
- temperature: float = 0.6,
- top_p: float = 0.9,
- top_k: int = 50,
- repetition_penalty: float = 1.2,
-) -> Iterator[str]:
- conversation = []
- for user, assistant in chat_history:
- conversation.extend(
- [
- {"role": "user", "content": user},
- {"role": "assistant", "content": assistant},
- ]
- )
- conversation.append({"role": "user", "content": message})
+ messages.append({"role": "user", "content": message})
 
- input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt")
- if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
- input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
- gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
- input_ids = input_ids.to(model.device)
+ response = ""
 
- streamer = TextIteratorStreamer(tokenizer, timeout=20.0, skip_prompt=True, skip_special_tokens=True)
- generate_kwargs = dict(
- {"input_ids": input_ids},
- streamer=streamer,
- max_new_tokens=max_new_tokens,
- do_sample=True,
- top_p=top_p,
- top_k=top_k,
+ for message in client.chat_completion(
+ messages,
+ max_tokens=max_tokens,
+ stream=True,
  temperature=temperature,
- num_beams=1,
- repetition_penalty=repetition_penalty,
- )
- t = Thread(target=model.generate, kwargs=generate_kwargs)
- t.start()
-
- outputs = []
- for text in streamer:
- outputs.append(text)
- yield "".join(outputs)
+ top_p=top_p,
+ ):
+ token = message.choices[0].delta.content
 
+ response += token
+ yield response
 
-chat_interface = gr.ChatInterface(
- fn=generate,
+"""
+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(
- label="Max new tokens",
- minimum=1,
- maximum=MAX_MAX_NEW_TOKENS,
- step=1,
- value=DEFAULT_MAX_NEW_TOKENS,
- ),
- gr.Slider(
- label="Temperature",
  minimum=0.1,
- maximum=4.0,
- step=0.1,
- value=0.6,
- ),
- gr.Slider(
- label="Top-p (nucleus sampling)",
- minimum=0.05,
  maximum=1.0,
+ value=0.95,
  step=0.05,
- value=0.9,
- ),
- gr.Slider(
- label="Top-k",
- minimum=1,
- maximum=1000,
- step=1,
- value=50,
- ),
- gr.Slider(
- label="Repetition penalty",
- minimum=1.0,
- maximum=2.0,
- step=0.05,
- value=1.2,
+ label="Top-p (nucleus sampling)",
  ),
  ],
- stop_btn=None,
- examples=[
- ["Hello there! How are you doing?"],
- ["Can you explain briefly to me what is the Python programming language?"],
- ["Explain the plot of Cinderella in a sentence."],
- ["How many hours does it take a man to eat a Helicopter?"],
- ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
- ],
- cache_examples=False,
 )
 
-with gr.Blocks(css="style.css", fill_height=True) as demo:
- gr.Markdown(DESCRIPTION)
- gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
- chat_interface.render()
 
 if __name__ == "__main__":
- demo.queue(max_size=20).launch()
+ demo.launch()