Upload 10 files

app.py

@@ -0,0 +1,82 @@
+from transformers import pipeline, AutoModelForSeq2SeqLM, AutoTokenizer
+import gradio as gr
+import re
+
+model_link = "text_summary_model"
+model = AutoModelForSeq2SeqLM.from_pretrained(model_link)
+tokenizer = AutoTokenizer.from_pretrained(model_link)
+
+pipe = pipeline('summarization', model=model, tokenizer=tokenizer)
+gen_kwargs = {'length_penalty': 0.8, 'num_beams': 8, "min_length": 30}
+
+
+def dummy_summarize(text):
+    text = clean_text(text)
+    return pipe(text, **gen_kwargs)[0]['summary_text']
+
+
+def clean_text(text):
+    # Remove Byte Order Marks (BOM)
+    text = text.replace('\ufeff', '')
+    # Replace \n with a space
+    text = text.replace('\n', ' ')
+    # Replace \r with a space
+    text = text.replace('\r', ' ')
+    # Remove backslashes
+    text = text.replace('\\', '')
+    # Remove Non-ASCII characters
+    text = re.sub(r'[^\x00-\x7F]+', '', text)
+    # Remove Non-printable characters
+    text = re.sub(r'[\x00-\x1F\x7F-\x9F]', '', text)
+    # Normalize whitespace
+    text = ' '.join(text.split())
+    return text
+
+
+# Custom HTML and CSS for the title and theme
+title_html = """
+<h1 style="font-size: 40px; text-align: center; color: white;">Text Summarization</h1>
+<p style="text-align: center; color: white; font-size:20px">Enter text to summarize it.</p>
+"""
+
+css = """
+body {
+    background-color: #007BFF;
+    color: white;
+}
+
+.gr-textbox textarea {
+    background-color: #0056b3;
+    color: white;
+    border: 2px solid white;
+}
+
+.gr-button {
+    background-color: #0056b3;
+    color: white;
+    border: 2px solid white;
+}
+
+.gr-button:hover {
+    background-color: #004080;
+}
+
+.gr-textbox input {
+    background-color: #0056b3;
+    color: white;
+    border: 2px solid white;
+}
+"""
+
+# Create a Gradio interface with large input and output textboxes
+interface = gr.Interface(
+    fn=dummy_summarize,
+    inputs=gr.Textbox(lines=15, placeholder="Enter text here..."),
+    outputs=gr.Textbox(lines=15, placeholder="Summary will appear here..."),
+    description=title_html,
+    theme="compact",  # Use compact theme to reduce padding
+    css=css
+)
+
+# Launch the interface
+interface.launch()

text_summary_model/config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "facebook/bart-large-cnn",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "max_position_embeddings": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 50264
+}

text_summary_model/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "min_length": 56,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.4"
+}

text_summary_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e42541a15e2f35e73d3fb8ad9240f5c3c130bdc365e7378265b9314a886cda5f
+size 1625422896

text_summary_model/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

text_summary_model/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

text_summary_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2bf0ae5f5b15c697a57a75f391c841ce31ad72cb0cf57c5629be83c616650a9
+size 5112