|
|
from huggingface_hub import InferenceClient |
|
|
import gradio as gr |
|
|
import random |
|
|
import pandas as pd |
|
|
from io import BytesIO |
|
|
|
|
|
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1") |
|
|
|
|
|
def extract_text_from_excel(file): |
|
|
df = pd.read_excel(file) |
|
|
text = ' '.join(df['data'].astype(str)) |
|
|
return text |
|
|
|
|
|
def generate_sentences(text, temperature, max_new_tokens, top_p, repetition_penalty): |
|
|
sentences = text.split('.') |
|
|
random.shuffle(sentences) |
|
|
|
|
|
generated_data = [] |
|
|
|
|
|
for sentence in sentences: |
|
|
sentence = sentence.strip() |
|
|
if not sentence: |
|
|
continue |
|
|
|
|
|
generate_kwargs = { |
|
|
"temperature": temperature, |
|
|
"max_new_tokens": max_new_tokens, |
|
|
"top_p": top_p, |
|
|
"repetition_penalty": repetition_penalty, |
|
|
"do_sample": True, |
|
|
"seed": 42, |
|
|
} |
|
|
|
|
|
try: |
|
|
stream = client.text_generation(sentence, **generate_kwargs, stream=True, details=True, return_full_text=False) |
|
|
output = "" |
|
|
for response in stream: |
|
|
output += response.token.text |
|
|
|
|
|
generated_sentences = [s.strip() for s in output.split('.') if s.strip()] |
|
|
generated_data.extend([(sentence, generated_sentence) for generated_sentence in generated_sentences]) |
|
|
|
|
|
except Exception as e: |
|
|
print(f"Error generating data for sentence '{sentence}': {e}") |
|
|
|
|
|
return generated_data |
|
|
|
|
|
def save_to_csv(data, filename="synthetic_data.csv"): |
|
|
with open(filename, mode='w', newline='', encoding='utf-8') as file: |
|
|
writer = csv.writer(file) |
|
|
writer.writerow(['Original Sentence', 'Generated Sentence']) |
|
|
writer.writerows(data) |
|
|
|
|
|
def generate(file, temperature, max_new_tokens, top_p, repetition_penalty): |
|
|
text = extract_text_from_excel(file) |
|
|
data = generate_sentences(text, temperature, max_new_tokens, top_p, repetition_penalty) |
|
|
save_to_csv(data) |
|
|
return gr.File.update(value=filename, visible=True) |
|
|
|
|
|
gr.Interface( |
|
|
fn=generate, |
|
|
inputs=[ |
|
|
gr.File(label="Upload Excel File", file_count="single", file_types=[".xlsx"]), |
|
|
gr.Slider(label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Higher values produce more diverse outputs"), |
|
|
gr.Slider(label="Max new tokens", value=256, minimum=0, maximum=5120, step=64, interactive=True, info="The maximum numbers of new tokens"), |
|
|
gr.Slider(label="Top-p (nucleus sampling)", value=0.95, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more low-probability tokens"), |
|
|
gr.Slider(label="Repetition penalty", value=1.0, minimum=1.0, maximum=2.0, step=0.1, interactive=True, info="Penalize repeated tokens"), |
|
|
], |
|
|
outputs=gr.File(label="Synthetic Data"), |
|
|
title="SDG", |
|
|
description="AYE QABIL.", |
|
|
allow_flagging="never", |
|
|
).launch() |
