Upload 23 files

.gitattributes

@@ -1,35 +1,4 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+resultscheckpoint-144model-144model.safetensors filter=lfs diff=lfs merge=lfs -text
+resultscheckpoint-144optimizer.pt filter=lfs diff=lfs merge=lfs -text
+results/checkpoint-144/model.safetensors filter=lfs diff=lfs merge=lfs -text
+results/checkpoint-144/optimizer.pt filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,30 @@
+from flask import Flask, request, send_file, render_template
+from main import create_docx_from_text
+import os
+
+app = Flask(__name__)
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+@app.route('/process', methods=['POST'])
+def process():
+    try:
+        user_text = request.form['text']
+        create_docx_from_text(user_text)
+
+        output_path = os.path.abspath("output.docx")
+        print("📄 Абсолютный путь к файлу:", output_path)
+
+        if not os.path.exists(output_path):
+            raise FileNotFoundError(f"Файл не найден: {output_path}")
+
+        return send_file(output_path, as_attachment=True, download_name="output.docx")
+
+    except Exception as e:
+        print("❌ Ошибка при обработке текста:", str(e))
+        return f"Ошибка при обработке текста: {str(e)}", 500
+
+if __name__ == '__main__':
+    app.run(debug=True)

main.py

@@ -0,0 +1,78 @@
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+import torch
+from docx import Document
+from docx.enum.text import WD_ALIGN_PARAGRAPH
+import os
+
+# Определите, где запускается код (CPU или GPU)
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+print(f"Используем устройство: {device}")
+
+# Загрузите обученную модель и токенизатор
+model_name = "C:\\Users\\khape\\Documents\\GitHub\\neuro-formatter\\results\checkpoint-144"
+
+try:
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForSeq2SeqLM.from_pretrained(model_name).to(device)
+    print("✅ Модель и токенизатор успешно загружены")
+except Exception as e:
+    print(f"❌ Ошибка при загрузке модели: {e}")
+    exit()
+
+# 🧠 Функция для генерации заголовка и текста
+def generate_title_and_split_text(text, model, tokenizer):
+    input_text = "summarize: " + text
+    input_tokenized = tokenizer(
+        input_text,
+        max_length=4096,
+        padding="max_length",
+        truncation=True,
+        return_tensors="pt"
+    ).to(device)
+
+    generated_output = model.generate(
+        input_ids=input_tokenized.input_ids,
+        attention_mask=input_tokenized.attention_mask,
+        max_length=512,
+        num_beams=5,
+        temperature=1.0
+    )
+
+    predicted_summary = tokenizer.decode(generated_output[0], skip_special_tokens=True)
+
+    # Пытаемся извлечь заголовок
+    try:
+        header_start = predicted_summary.index("[HEADER] ") + len("[HEADER] ")
+        header_end = predicted_summary.index(" [NEW_PARAGRAPH] ")
+        header = predicted_summary[header_start:header_end]
+    except ValueError:
+        words = text.split()
+        header = " ".join(words[:7])
+
+    # Форматирование текста
+    formatted_text = text.replace(". ", ".\n[NEW_PARAGRAPH] ")
+    formatted_text = formatted_text.replace("[NEW_PARAGRAPH]", "\t")
+
+    return header, formatted_text
+
+# 📄 Функция для Flask (и ручного запуска)
+def create_docx_from_text(text):
+    print("⚙️ create_docx_from_text() вызвана")
+    header, formatted_text = generate_title_and_split_text(text, model, tokenizer)
+
+    paragraphs = formatted_text.split('\n[NEW_PARAGRAPH]\t')
+    formatted_text_with_spaces = "\n\n".join(["       " + p for p in paragraphs])
+
+    document = Document()
+    heading = document.add_heading(header, level=1)
+    heading.alignment = WD_ALIGN_PARAGRAPH.CENTER
+    document.add_paragraph(formatted_text_with_spaces)
+
+    output_path = os.path.abspath("output.docx")
+    document.save(output_path)
+    print(f"✅ output.docx успешно создан: {output_path}")
+
+# 🔍 Пример запуска
+if __name__ == "__main__":
+    sample_text = "Пример текста, который будет обработан моделью."
+    create_docx_from_text(sample_text)

results/checkpoint-144/config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LongT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "encoder_attention_type": "local",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "global_block_size": 16,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "local_radius": 127,
+  "model_type": "longt5",
+  "n_positions": 4096,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.2",
+  "use_cache": true,
+  "vocab_size": 32102
+}

results/checkpoint-144/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.52.2"
+}

results/checkpoint-144/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f711ae7f293599a84bef8e20a8ebf4c6f10000cc8b48717ff71671f38048ee
+size 990185568

results/checkpoint-144/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642f981f4a0227e180a5497fd107d7c36f903ae2990cf6f26381d8ba580d5c41
+size 1980533451

results/checkpoint-144/special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

results/checkpoint-144/tokenizer_config.json

@@ -0,0 +1,955 @@
+{
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32100": {
+      "content": "[HEADER]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32101": {
+      "content": "[NEW_PARAGRAPH]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

results/checkpoint-144/trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 100,
+  "max_steps": 18,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 195138363064320.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

static/script.js

@@ -0,0 +1,28 @@
+function register() {
+    const email = document.getElementById('regEmail').value;
+    const password = document.getElementById('regPassword').value;
+
+    if (!email || !password) {
+        alert('Please fill in all fields.');
+        return;
+    }
+
+    localStorage.setItem('userEmail', email);
+    localStorage.setItem('userPassword', password);
+    window.location.href = 'login.html';
+}
+
+function login() {
+    const email = document.getElementById('logEmail').value;
+    const password = document.getElementById('logPassword').value;
+
+    const storedEmail = localStorage.getItem('userEmail');
+    const storedPassword = localStorage.getItem('userPassword');
+
+    if (email === storedEmail && password === storedPassword) {
+        localStorage.setItem('loggedIn', true);
+        window.location.href = 'index.html';
+    } else {
+        alert('Invalid credentials.');
+    }
+}

static/style.css

@@ -0,0 +1,174 @@
+body {
+    margin: 0;
+    font-family: 'Segoe UI', sans-serif;
+    background: linear-gradient(to bottom right, #ffffff, #f3f1ff);
+    height: 100vh;
+    overflow: hidden;
+    display: flex;
+    flex-direction: column;
+}
+
+.header {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    padding: 1rem 2rem;
+    background-color: #fff;
+    border-bottom: 1px solid #eee;
+}
+
+.logo {
+    display: flex;
+    align-items: center;
+    gap: 0.75rem;
+}
+
+.logo img {
+    height: 40px;
+}
+
+.buttons {
+    display: flex;
+    gap: 1rem;
+}
+
+.buttons button {
+    padding: 0.5rem 1.25rem;
+    border: 1px solid #ccc;
+    border-radius: 20px;
+    cursor: pointer;
+    font-weight: 500;
+}
+
+.buttons .login-button {
+    background: linear-gradient(91deg,
+            rgba(167, 255, 239, 0.3) 0%,
+            rgba(255, 210, 223, 0.25) 18%,
+            rgba(153, 255, 194, 0.18) 40%,
+            rgba(96, 139, 204, 0.09) 70%,
+            rgba(255, 153, 0, 0) 100%);
+}
+
+.buttons .create-button {
+    background: linear-gradient(91deg,
+            rgba(167, 255, 239, 0.7) 0%,
+            rgba(255, 210, 223, 0.58) 18%,
+            rgba(153, 255, 194, 0.42) 40%,
+            rgba(96, 139, 204, 0.21) 70%,
+            rgba(255, 153, 0, 0) 100%);
+}
+
+.main-container {
+    display: flex;
+    flex: 1;
+    overflow: hidden;
+}
+
+.left-sidebar {
+    width: 15%;
+    padding: 1rem;
+    display: flex;
+    flex-direction: column;
+    gap: 1rem;
+}
+
+.right-sidebar {
+    width: 20%;
+    padding: 1rem;
+    display: flex;
+    flex-direction: column;
+    gap: 1rem;
+}
+.sidebar-card {
+    flex: 1;
+    background: linear-gradient(to bottom right, #fff, #f4efff);
+    border-radius: 16px;
+    padding: 1rem;
+    box-shadow: 0 4px 16px rgba(0, 0, 0, 0.05);
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    text-align: center;
+}
+
+.chat-section {
+    flex: 1;
+    position: relative;
+    padding: 2rem;
+    display: flex;
+    flex-direction: column;
+    justify-content: flex-end;
+    background: radial-gradient(circle at 70% 30%, #f5f3ff, #ffffff);
+}
+
+.chat-header {
+    text-align: center;
+    margin-bottom: 20rem;
+    font-size: 1.25rem;
+}
+
+.chat-header .sparkles {
+    font-size: 1.5rem;
+    display: block;
+}
+
+.chat-window {
+    overflow-y: auto;
+    max-height: 900px;
+    margin-bottom: 1rem;
+    display: flex;
+    flex-direction: column;
+    gap: 0.75rem;
+}
+
+.message {
+    max-width: 70%;
+    padding: 1rem;
+    border-radius: 12px;
+    font-size: 0.95rem;
+    line-height: 1.4;
+}
+
+.message.user {
+    background: #ffffff;
+    align-self: flex-end;
+}
+
+.message.ai {
+    background: #f4efff;
+    align-self: flex-start;
+}
+
+.chat-input {
+    display: flex;
+    align-items: center;
+    gap: 0.5rem;
+}
+
+.chat-input input {
+    flex: 1;
+    padding: 0.75rem 1rem;
+    border: 1px solid #ccc;
+    border-radius: 25px;
+}
+
+.chat-input button {
+    background: none;
+    border: none;
+    font-size: 1.25rem;
+    cursor: pointer;
+}
+
+.social-icons {
+    position: absolute;
+    bottom: 1rem;
+    right: 2rem;
+    display: flex;
+    gap: 1.5rem;
+}
+
+.social-icons a {
+    color: #444;
+    font-size: 1.5rem;
+}
+

templates/index.html

@@ -0,0 +1,90 @@
+<!DOCTYPE html>
+<html lang="en">
+    
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Neuro Formatter</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='style.css') }}">
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/css/all.min.css">
+</head>
+<body>
+    <header class="header">
+        <div class="logo">
+            <img src="https://c.animaapp.com/fKcvUkrz/img/logo@2x.png" alt="Logo">
+            <img src="https://c.animaapp.com/fKcvUkrz/img/brand-name@2x.png" alt="brand-name"/>
+        </div>
+        <div class="buttons">
+            <a href="login.html" target="_blank"><button class="login-button">Login</button></a>
+            <a href="register.html" target="_blank"><button class="create-button">Create account</button></a>
+        </div>
+    </header>
+
+    <main class="main-container">
+        <aside class="left-sidebar">
+            <div class="sidebar-card">This could be your ad</div>
+            <div class="sidebar-card">This could be your ad</div>
+        </aside>
+
+        <section class="chat-section">
+            <div class="chat-window">
+                <div class="chat-header">
+                    <span class="sparkles">✨</span>
+                    <h2>Just relax and enjoy the era you were born into</h2>
+                </div>
+                <div class="message user">What can I ask you to do?</div>
+                <div class="message ai">
+                    <strong>NF AI</strong><br>
+                    Great question! You can ask for my help with the following:
+                    <ol>
+                        <li>I can come up with a title for your text.</li>
+                        <li>I can break your text into meaningful paragraphs</li>
+                    </ol>
+                </div>
+            </div>
+
+            <div class="chat-input">
+                <form id="textForm">
+                    <input type="text" name="text" placeholder="Send me your text" required>
+                    <button type="submit"><i class="fa-solid fa-paper-plane"></i></button>
+                </form>
+            </div>
+        </section>
+
+        <aside class="right-sidebar">
+            <div class="social-icons">
+                <a href="#" target="_blank"><i class="fab fa-tiktok"></i></a>
+                <a href="#" target="_blank"><i class="fab fa-vk"></i></a>
+                <a href="#" target="_blank"><i class="fab fa-telegram"></i></a>
+                <a href="#" target="_blank"><i class="fas fa-envelope"></i></a>
+            </div>
+        </aside>
+    </main>
+
+    <script>
+    document.getElementById('textForm').addEventListener('submit', async function (e) {
+        e.preventDefault();
+        const formData = new FormData(this);
+
+        const response = await fetch('/process', {
+            method: 'POST',
+            body: formData
+        });
+
+        if (response.ok) {
+            const blob = await response.blob();
+            const url = window.URL.createObjectURL(blob);
+            const a = document.createElement('a');
+            a.href = url;
+            a.download = 'output.docx'; // Изменено тут
+            document.body.appendChild(a);
+            a.click();
+            a.remove();
+        } else {
+            alert('Ошибка при обработке запроса');
+        }
+    });
+</script>
+
+</body>
+</html>

templates/login.html

@@ -0,0 +1,22 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8" />
+    <title>Login</title>
+    <link rel="stylesheet" href="zstyle.css" />
+</head>
+
+<body>
+    <div class="container">
+        <h2>Login</h2>
+        <input type="email" id="logEmail" placeholder="Email" />
+        <input type="password" id="logPassword" placeholder="Password" />
+        <button onclick="login()">Login</button>
+        <p>Don't have an account? <a href="register.html">Register</a></p>
+    </div>
+
+    <script src="script.js"></script>
+</body>
+
+</html>

templates/register.html

@@ -0,0 +1,22 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8" />
+    <title>Register</title>
+    <link rel="stylesheet" href="zstyle.css" />
+</head>
+
+<body>
+    <div class="container">
+        <h2>Register</h2>
+        <input type="email" id="regEmail" placeholder="Email" />
+        <input type="password" id="regPassword" placeholder="Password" />
+        <button onclick="register()">Create Account</button>
+        <p>Already have an account? <a href="login.html">Login</a></p>
+    </div>
+
+    <script src="script.js"></script>
+</body>
+
+</html>