Upload 11 files

README.md

@@ -1,13 +1,12 @@
 ---
-title: Spoiler Alert Plot Summary Generator
-emoji: 🦀
-colorFrom: blue
-colorTo: purple
+title: Spoiler Alert
+emoji: 🌍
+colorFrom: gray
+colorTo: indigo
 sdk: gradio
 sdk_version: 4.44.0
 app_file: app.py
 pinned: false
-short_description: non-spoiler-Plot-Summary-Generator
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,45 @@
+import gradio as gr
+from transformers import LEDForConditionalGeneration, LEDTokenizer
+import torch
+from datasets import load_dataset
+import re
+
+# Set device to GPU if available
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load the LED model and tokenizer
+model = LEDForConditionalGeneration.from_pretrained("./summary_generation_Led_4").to(device)
+tokenizer = LEDTokenizer.from_pretrained("./summary_generation_Led_4")
+
+# Normalize the input text (plot synopsis)
+def normalize_text(text):
+    text = text.lower()  # Lowercase the text
+    text = re.sub(r'\s+', ' ', text).strip()  # Remove extra spaces and newlines
+    text = re.sub(r'[^\w\s]', '', text)  # Remove non-alphanumeric characters
+    return text
+
+# Function to preprocess and generate summaries
+def generate_summary(plot_synopsis):
+    # Preprocess the plot_synopsis
+    inputs = tokenizer("summarize: " + normalize_text(plot_synopsis), 
+                       max_length=3000, truncation=True, padding="max_length", return_tensors="pt")
+    inputs = inputs.to(device)
+
+    # Generate the summary
+    outputs = model.generate(inputs["input_ids"], max_length=315, min_length=20, 
+                             length_penalty=2.0, num_beams=4, early_stopping=True)
+    
+    summary = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return summary
+
+# Gradio interface to take plot synopsis and output a generated summary
+interface = gr.Interface(
+    fn=generate_summary,
+    inputs=gr.Textbox(label="Plot Synopsis", lines=10, placeholder="Enter the plot synopsis here..."),
+    outputs=gr.Textbox(label="Generated Summary"),
+    title="Plot Summary Generator",
+    description="This demo generates a plot summary based on the plot synopsis using a fine-tuned LED model."
+)
+
+# Launch the Gradio interface
+interface.launch()

requirements.txt

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

summary_generation_Led_4/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/summary_generation",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "LEDForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_window": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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
+  },
+  "max_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 16384,
+  "model_type": "led",
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 50265
+}

summary_generation_Led_4/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.4"
+}

summary_generation_Led_4/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f023dedaee3beff15d69b6dcf007839030bacdabc661fb606b7ad95d1dfc99
+size 134

summary_generation_Led_4/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

summary_generation_Led_4/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": 16384,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LEDTokenizer",
+  "unk_token": "<unk>"
+}

summary_generation_Led_4/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3addcd03e4df756227df87319ee2ce381285458b47ad8112d6bdb9baf62749
+size 129