Spaces:
Sleeping
Sleeping
File size: 2,836 Bytes
8fcc055 5c8be37 8fcc055 f27161f 5c8be37 f27161f 911ff06 5c8be37 911ff06 5c8be37 8fcc055 911ff06 5c8be37 8fcc055 5c8be37 8fcc055 5c8be37 8fcc055 911ff06 5c8be37 8fcc055 1e7eb99 911ff06 5c8be37 8fcc055 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
"""
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
"""
# Load the model and tokenizer
model_name = "vennify/t5-base-grammar-correction"
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
def correct_text(text, max_length, max_new_tokens=0, min_length, num_beams, temperature, top_p):
inputs = tokenizer.encode(text, return_tensors="pt")
if max_new_tokens > 0:
outputs = model.generate(
inputs,
max_length=max_length,
max_new_tokens=max_new_tokens,
min_length=min_length,
num_beams=num_beams,
temperature=temperature,
top_p=top_p,
early_stopping=True
)
else:
outputs = model.generate(
inputs,
max_length=max_length,
min_length=min_length,
num_beams=num_beams,
temperature=temperature,
top_p=top_p,
early_stopping=True
)
corrected_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
return corrected_text
def respond(message, history: list[tuple[str, str]], system_message, max_length, min_length, max_new_tokens, num_beams, 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 = correct_text(message, max_length, max_new_tokens, min_length, num_beams, temperature, top_p)
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=100, step=1, label="Max Length"),
gr.Slider(minimum=1, maximum=2048, value=0, step=1, label="Min Length"),
gr.Slider(minimum=1, maximum=2048, value=0, step=1, label="Max New Tokens (optional)"),
gr.Slider(minimum=1, maximum=10, value=5, step=1, label="Num Beams"),
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() |