app is done

app.py

@@ -0,0 +1,61 @@
+import streamlit as st
+from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
+import torch
+import json
+
+model = DistilBertForSequenceClassification.from_pretrained('./arxiv_classifier')
+tokenizer = DistilBertTokenizer.from_pretrained('./arxiv_classifier')
+
+with open('./arxiv_classifier/index_to_category.json', 'r', encoding='utf-8') as f:
+    index_to_category = json.load(f)
+
+def predict(title, summary):
+    inputs = tokenizer(title + " " + summary, return_tensors="pt", padding=True, truncation=True)
+    outputs = model(**inputs)
+    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    return predictions
+
+st.set_page_config(page_title="ArXiv Article Classifier", layout="centered")
+
+st.title("ArXiv Article Classifier")
+st.write("Введите заголовок и аннотацию статьи, чтобы получить предсказание категории.")
+
+title = st.text_input("Заголовок статьи", placeholder="Введите заголовок статьи здесь")
+summary = st.text_area("Аннотация статьи", placeholder="Введите аннотацию статьи здесь")
+
+# Кнопка для классификации
+if st.button("Классифицировать"):
+    if title.strip() == "" and summary.strip() == "":
+        st.error("Пожалуйста, введите заголовок или аннотацию статьи.")
+    else:
+        with st.spinner("Классификация..."):
+            predictions = predict(title, summary)
+            sorted_indices = torch.argsort(predictions[0], descending=True)
+            cumulative_probability = 0.0
+            st.subheader("Результаты классификации:")
+            for idx in sorted_indices:
+                probability = predictions[0][idx].item()
+                cumulative_probability += probability
+                category_name = index_to_category.get(str(idx.item()), "Unknown")
+                st.write(f"Категория {category_name}: {probability:.2f}")
+                if cumulative_probability >= 0.95:
+                    break
+
+st.markdown(
+    """
+    <style>
+    .stButton>button {
+        background-color: #4CAF50;
+        color: white;
+        padding: 10px 24px;
+        border: none;
+        border-radius: 4px;
+        cursor: pointer;
+    }
+    .stButton>button:hover {
+        background-color: #45a049;
+    }
+    </style>
+    """,
+    unsafe_allow_html=True
+)

arxiv_classifier/config.json

@@ -0,0 +1,93 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.3",
+  "vocab_size": 28996
+}

arxiv_classifier/index_to_category.json

@@ -0,0 +1,34 @@
+{
+    "0": "cs.SI",
+    "1": "cs.SD",
+    "2": "cs.RO",
+    "3": "cs.DC",
+    "4": "cs.OS",
+    "5": "stat.ML",
+    "6": "cs.CR",
+    "7": "cs.SE",
+    "8": "cs.LG",
+    "9": "eess.AS",
+    "10": "cs.NI",
+    "11": "astro-ph.IM",
+    "12": "astro-ph.EP",
+    "13": "eess.SY",
+    "14": "cs.MM",
+    "15": "cs.CV",
+    "16": "cs.GR",
+    "17": "cs.AI",
+    "18": "math.OC",
+    "19": "cs.GT",
+    "20": "cs.CL",
+    "21": "cs.HC",
+    "22": "cs.DB",
+    "23": "q-bio.QM",
+    "24": "cs.DS",
+    "25": "cs.CY",
+    "26": "cs.DM",
+    "27": "cs.MA",
+    "28": "eess.SP",
+    "29": "q-bio.BM",
+    "30": "cs.IR",
+    "31": "eess.IV"
+}

arxiv_classifier/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344b60cef9157ff25876033fd760d0e2a44b92ad6500127c6e570b957962725b
+size 263236976

arxiv_classifier/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

arxiv_classifier/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

requirements.txt

@@ -0,0 +1,3 @@
+streamlit
+transformers
+torch