Spaces:
Sleeping
Sleeping
File size: 1,661 Bytes
943943c afbd689 943943c c81c814 943943c 2762217 943943c c81c814 2762217 943943c c81c814 943943c c81c814 943943c c81c814 943943c b9f6470 943943c |
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 |
import gradio as gr
import os
from huggingface_hub import InferenceClient
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
"""
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")
access_token=os.environ['token']
# Load Model
model_directory = 'paulpall/GEC_Estonian_OPUS-MT'
tokenizer = AutoTokenizer.from_pretrained(model_directory, token=access_token)
model = AutoModelForSeq2SeqLM.from_pretrained(model_directory, token=access_token)
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})
# Generate corrected sentence
input_ids = tokenizer.encode(message, padding='max_length', truncation=True, max_length=128, return_tensors='pt')
output_ids = model.generate(input_ids=input_ids.to(model.device))
output_sentence = tokenizer.decode(output_ids[0], skip_special_tokens=True).replace(r"▁",r" ")
response = output_sentence
yield response
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
respond
)
if __name__ == "__main__":
demo.launch() |