new model

app.py

@@ -1,4 +1,5 @@
 import streamlit as st
+import torch
 
 st.markdown("# Arxiv classifier")
 title = st.text_input('*Article title:')
@@ -50,14 +51,21 @@ class_label = ClassLabel(names=categories_tags)
 
 @st.cache
 def get_model():
-    return AutoModelForSequenceClassification.from_pretrained('./arxiv_model', num_labels=len(categories_tags))
+    return AutoModelForSequenceClassification.from_pretrained('./arxiv_model_2000', num_labels=len(categories_tags))
 
 
 model = get_model()
 
-if title:
+
+@torch.inference_mode()
+def print_results():
     name_by_category = get_name_by_category()
     input_tensor = tokenizer(title, abstract, padding="max_length", truncation=True, return_tensors='pt')
+    st.markdown('## Results:')
     for probability, label_index in top95(model(**input_tensor).logits):
         category = class_label.int2str(label_index)
         st.markdown(f'{round(probability, 2)} – {category} ({name_by_category[category]})')
+
+
+if title:
+    print_results()

arxiv_model_2000/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "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"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "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": "4.17.0",
+  "vocab_size": 28996
+}

arxiv_model_2000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ecd4b5d58ed2a4e3dc73692c8b9aa83f934137f79b9db2cc007736024d6655
+size 263181873

arxiv_model_2000/special_tokens_map.json

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

arxiv_model_2000/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-cased", "tokenizer_class": "DistilBertTokenizer"}

arxiv_model_2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:666e819549f78d5d59e2e9097cdbabe18f637d029d76bee1ae9295914bd8992a
+size 2991