Upload 10 files

app.py

@@ -0,0 +1,35 @@
+import streamlit as st
+from transformers import pipeline
+
+st.set_page_config(page_title="AI TL;DR Tool", page_icon="📝")
+@st.cache_resource
+def load_summarizer():
+    return pipeline("summarization", model="./summarizer_model")
+
+summarizer = load_summarizer()
+
+st.title("Automated Text Summarizer")
+st.subheader("Generate a 2-3 sentence summary of long articles or legal docs.")
+
+text_to_summarize = st.text_area("Paste your long text here:", height=300)
+
+with st.sidebar:
+    st.header("Settings")
+    max_len = st.slider("Max Summary Length", 30, 150, 75)
+    min_len = st.slider("Min Summary Length", 10, 50, 25)
+
+if st.button("Generate TL;DR"):
+    if text_to_summarize.strip():
+        with st.spinner("Analyzing and condensing..."):
+            output = summarizer(
+                text_to_summarize, 
+                max_length=max_len, 
+                min_length=min_len, 
+                do_sample=False
+            )
+            
+            st.success("Summary Generated")
+            st.write(f"### Result:")
+            st.write(output[0]['summary_text'])
+    else:
+        st.warning("Please paste some text first!")

model.py

@@ -0,0 +1,9 @@
+from transformers import pipeline
+
+model_name = "facebook/bart-large-cnn"
+summarizer = pipeline("summarization", model=model_name)
+
+# Save the model and tokenizer to a local directory
+# This is the Hugging Face standard for 'pickling' a model
+summarizer.save_pretrained("./summarizer_model")
+print("Model saved successfully to ./summarizer_model")

summarizer_model/config.json

@@ -0,0 +1,69 @@
+{
+  "_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": null,
+  "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_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": null,
+  "max_length": null,
+  "max_position_embeddings": 1024,
+  "min_length": null,
+  "model_type": "bart",
+  "no_repeat_ngram_size": null,
+  "normalize_before": false,
+  "num_beams": null,
+  "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": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

summarizer_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": "4.49.0"
+}

summarizer_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>"
+}

summarizer_model/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

tempCodeRunnerFile.python

@@ -0,0 +1,12 @@
+import os
+
+# This prints the full path to where your model folder is located
+print("Your model is here:")
+print(os.path.abspath("./summarizer_model"))
+
+# This checks if the files actually exist inside
+if os.path.exists("./summarizer_model"):
+    print("\nFiles found:")
+    print(os.listdir("./summarizer_model"))
+else:
+    print("\nFolder not found! Run the save script first.")