Spaces:
Build error
Build error
File size: 2,609 Bytes
d3a4db4 e02ddf7 d3a4db4 e02ddf7 d3a4db4 e02ddf7 d3a4db4 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
from flask import Flask, request, jsonify
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch
import gradio as gr
from huggingface_hub import InferenceClient
app = Flask(__name__)
tokenizer = AutoTokenizer.from_pretrained("sshleifer/distilbart-cnn-12-6")
model = AutoModelForSeq2SeqLM.from_pretrained("sshleifer/distilbart-cnn-12-6")
"""
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")
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
@app.route('/summarize', methods=['POST'])
def summarize():
data = request.json
text = data.get('text', '')
if not text:
return jsonify({'error': 'No text provided'}), 400
inputs = tokenizer([text], max_length=1024, return_tensors="pt", truncation=True)
summary_ids = model.generate(inputs["input_ids"], max_length=60, min_length=10, length_penalty=2.0, num_beams=4, early_stopping=True)
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
return jsonify({'summary': summary})
"""
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__':
from waitress import serve
serve(app, host='0.0.0.0', port=5005)
demo.launch() |