|
import json |
|
from huggingface_hub import InferenceClient |
|
import gradio as gr |
|
import random |
|
import pandas as pd |
|
from io import BytesIO |
|
import csv |
|
import os |
|
import io |
|
import tempfile |
|
import re |
|
|
|
|
|
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1") |
|
|
|
def extract_sentences_from_excel(file): |
|
df = pd.read_excel(file) |
|
sentences = df['metn'].astype(str).tolist() |
|
return sentences |
|
|
|
def generate(file, prompt, temperature, max_new_tokens, top_p, repetition_penalty): |
|
sentences = extract_sentences_from_excel(file) |
|
data = [] |
|
|
|
generate_kwargs = { |
|
"temperature": temperature, |
|
"max_new_tokens": max_new_tokens, |
|
"top_p": top_p, |
|
"repetition_penalty": repetition_penalty, |
|
"do_sample": True, |
|
"seed": 42, |
|
} |
|
|
|
for sentence in sentences: |
|
try: |
|
stream = client.text_generation(f"{prompt} Output the response in the following JSON format: {{'generated_sentence': 'The generated sentence text', 'confidence_score': 0.9}} {sentence}", **generate_kwargs, stream=True, details=True, return_full_text=False) |
|
output = "" |
|
for response in stream: |
|
output += response.token.text |
|
data.append({"original_sentence": sentence, "generated_data": output}) |
|
except Exception as e: |
|
print(f"Error generating data for sentence '{sentence}': {e}") |
|
|
|
filename = "synthetic_data.json" |
|
save_to_json(data, filename) |
|
|
|
return filename |
|
|
|
def save_to_json(data, filename): |
|
json_data = [] |
|
for item in data: |
|
generated_sentences = [] |
|
confidence_scores = [] |
|
for match in re.finditer(r"{'generated_sentence': '(.+?)', 'confidence_score': ([\d\.]+)}", item['generated_data']): |
|
generated_sentences.append(match.group(1)) |
|
confidence_scores.append(float(match.group(2))) |
|
json_data.append({ |
|
'original_sentence': item['original_sentence'], |
|
'generated_sentences': generated_sentences, |
|
'confidence_scores': confidence_scores |
|
}) |
|
|
|
with open(filename, mode='w', encoding='utf-8') as file: |
|
json.dump(json_data, file, indent=4, ensure_ascii=False) |
|
|
|
|
|
gr.Interface( |
|
fn=generate, |
|
inputs=[ |
|
gr.File(label="Upload Excel File", file_count="single", file_types=[".xlsx"]), |
|
gr.Textbox(label="Prompt", placeholder="Enter your prompt here"), |
|
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() |
