gfjgfj

app.py

@@ -1,76 +1,7 @@
-import datasets
-import evaluate
-import os
-import pandas as pd
-import numpy as np
-from datasets import Dataset
-from sklearn.model_selection import train_test_split
-from transformers import (AutoTokenizer, AutoModelForSequenceClassification,
-                          TrainingArguments, Trainer)
+import gradio as gr
 
-os.environ["CUDA_VISIBLE_DEVICES"] = ""
+def greet(name):
+    return "Hello " + name + "!!"
 
-model_name = "cointegrated/rubert-tiny2"
-
-# Login using e.g. `huggingface-cli login` to access this dataset
-splits = {'train': 'train.json', 'test': 'test.json'}
-df = pd.read_json("hf://datasets/Den4ikAI/gibberish_dataset/" + splits["train"])
-df = df.head(500)
-
-# Конвертируем датафрейм в Dataset
-train, test = train_test_split(df, test_size=0.2)
-train = Dataset.from_pandas(train)
-test = Dataset.from_pandas(test)
-
-# Выполняем предобработку текста
-tokenizer = AutoTokenizer.from_pretrained(model_name, max_len=400)
-
-def tokenize_function(examples):
-	return tokenizer(examples['text'], padding='max_length', truncation=True)
-
-tokenized_train = train.map(tokenize_function)
-tokenized_test = test.map(tokenize_function)
-
-# Загружаем предобученную модель
-model = AutoModelForSequenceClassification.from_pretrained(
-	model_name,
-	num_labels=4)
-
-model.to("cpu")
-
-# Задаем параметры обучения
-training_args = TrainingArguments(
-    output_dir='test_trainer_log',
-    eval_strategy='epoch',
-    per_device_train_batch_size=6,
-    per_device_eval_batch_size=6,
-    num_train_epochs=5,
-    report_to='none'
-)
-
-metric = evaluate.load('f1')
-def compute_metrics(eval_pred):
-    logits, labels = eval_pred
-    predictions = np.argmax(logits, axis=-1)
-    return metric.compute(
-        predictions=predictions,
-        references=labels,
-        average='micro'
-    )
-
-# Выполняем обучение
-trainer = Trainer(
-	model = model,
-	args = training_args,
-	train_dataset = tokenized_train,
-	eval_dataset = tokenized_test,
-	compute_metrics = compute_metrics)
-
-trainer.train()
-
-# Сохраняем модель
-save_directory = './pt_save_pretrained'
-#tokenizer.save_pretrained(save_directory)
-model.save_pretrained(save_directory)
-#alternatively save the trainer
-#trainer.save_model('CustomModels/CustomHamSpam')
+demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+demo.launch()

requirements.txt

@@ -1,9 +1,4 @@
 transformers
 torch
 accelerate
-bitsandbytes
-datasets
-evaluate
-pandas
-numpy
-scikit-learn
+bitsandbytes