Adding files

1. Transformer Models.ipynb

@@ -0,0 +1,691 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# TRANSFORMER MODELS"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Transformers, what can they do?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Sentiment Analysis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "No model was supplied, defaulted to distilbert/distilbert-base-uncased-finetuned-sst-2-english and revision 714eb0f (https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english).\n",
+      "Using a pipeline without specifying a model name and revision in production is not recommended.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From c:\\Users\\ACER\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\tf_keras\\src\\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[{'label': 'POSITIVE', 'score': 0.9598049521446228}]"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "classifier = pipeline(\"sentiment-analysis\")\n",
+    "classifier(\"I've been waiting for a HuggingFace course my whole life.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'label': 'POSITIVE', 'score': 0.9598049521446228},\n",
+       " {'label': 'NEGATIVE', 'score': 0.9994558691978455}]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# we can pass several sentences\n",
+    "classifier(\n",
+    "    [\"I've been waiting for a HuggingFace course my whole life.\", \"I hate this so much!\"]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Zero-shot classification"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "No model was supplied, defaulted to facebook/bart-large-mnli and revision d7645e1 (https://huggingface.co/facebook/bart-large-mnli).\n",
+      "Using a pipeline without specifying a model name and revision in production is not recommended.\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "13af57499d894e8aa77c7ed39138d3dd",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model.safetensors:  98%|#########8| 1.60G/1.63G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\ACER\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\huggingface_hub\\file_download.py:147: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\ACER\\.cache\\huggingface\\hub\\models--facebook--bart-large-mnli. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
+      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
+      "  warnings.warn(message)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5184b998013d4eacac2a0e943ebcbfdf",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "tokenizer_config.json:   0%|          | 0.00/26.0 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "af001870e23b4808862f0f4e160327ef",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "vocab.json:   0%|          | 0.00/899k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "743eb773e873441c813a1d13925215cf",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "merges.txt:   0%|          | 0.00/456k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "f29eb797c99242558fe742a00411262c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "tokenizer.json:   0%|          | 0.00/1.36M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'sequence': 'This is a course about the Transformers library.',\n",
+       " 'labels': ['education', 'business', 'politics'],\n",
+       " 'scores': [0.8719874024391174, 0.09406554698944092, 0.033947039395570755]}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "classifier = pipeline(\"zero-shot-classification\")\n",
+    "\n",
+    "classifier(\n",
+    "    \"This is a course about the Transformers library.\",\n",
+    "    candidate_labels = [\"education\", \"politics\", \"business\"]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Text generation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "No model was supplied, defaulted to openai-community/gpt2 and revision 607a30d (https://huggingface.co/openai-community/gpt2).\n",
+      "Using a pipeline without specifying a model name and revision in production is not recommended.\n",
+      "Setting `pad_token_id` to `eos_token_id`:None for open-end generation.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[{'generated_text': 'In this course, we will teach you how to build a custom script and a WebScript web server that uses the JQuery 4.3 framework.\\n\\nYou will run up to 60 minutes with a single setup, in our example JQuery J'}]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "generator = pipeline(\"text-generation\")\n",
+    "generator(\"In this course, we will teach you how to\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Using any model from the Hub in a pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Truncation was not explicitly activated but `max_length` is provided a specific value, please use `truncation=True` to explicitly truncate examples to max length. Defaulting to 'longest_first' truncation strategy. If you encode pairs of sequences (GLUE-style) with the tokenizer you can select this strategy more precisely by providing a specific strategy to `truncation`.\n",
+      "Setting `pad_token_id` to `eos_token_id`:None for open-end generation.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[{'generated_text': 'In this course, we will teach you how to implement an API that can only be used by a single user.\\n\\n\\nHere are the slides'},\n",
+       " {'generated_text': 'In this course, we will teach you how to put food in order to reduce the risk of heart disease and even kill yourself as part of a program'}]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "generator = pipeline(\"text-generation\", model=\"distilgpt2\")\n",
+    "\n",
+    "generator(\n",
+    "    \"In this course, we will teach you how to\",\n",
+    "    max_length=30,\n",
+    "    num_return_sequences=2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Mask filling"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "No model was supplied, defaulted to distilbert/distilroberta-base and revision fb53ab8 (https://huggingface.co/distilbert/distilroberta-base).\n",
+      "Using a pipeline without specifying a model name and revision in production is not recommended.\n",
+      "Some weights of the model checkpoint at distilbert/distilroberta-base were not used when initializing RobertaForMaskedLM: ['roberta.pooler.dense.bias', 'roberta.pooler.dense.weight']\n",
+      "- This IS expected if you are initializing RobertaForMaskedLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
+      "- This IS NOT expected if you are initializing RobertaForMaskedLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[{'score': 0.19198469817638397,\n",
+       "  'token': 30412,\n",
+       "  'token_str': ' mathematical',\n",
+       "  'sequence': 'This course will teach you all about mathematical models.'},\n",
+       " {'score': 0.04209211468696594,\n",
+       "  'token': 38163,\n",
+       "  'token_str': ' computational',\n",
+       "  'sequence': 'This course will teach you all about computational models.'}]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "unmasker = pipeline(\"fill-mask\")\n",
+    "unmasker(\"This course will teach you all about <mask> models.\", top_k=2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Named Entity Recognition"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "No model was supplied, defaulted to dbmdz/bert-large-cased-finetuned-conll03-english and revision 4c53496 (https://huggingface.co/dbmdz/bert-large-cased-finetuned-conll03-english).\n",
+      "Using a pipeline without specifying a model name and revision in production is not recommended.\n",
+      "Some weights of the model checkpoint at dbmdz/bert-large-cased-finetuned-conll03-english were not used when initializing BertForTokenClassification: ['bert.pooler.dense.bias', 'bert.pooler.dense.weight']\n",
+      "- This IS expected if you are initializing BertForTokenClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
+      "- This IS NOT expected if you are initializing BertForTokenClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
+      "c:\\Users\\ACER\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\transformers\\pipelines\\token_classification.py:170: UserWarning: `grouped_entities` is deprecated and will be removed in version v5.0.0, defaulted to `aggregation_strategy=\"AggregationStrategy.SIMPLE\"` instead.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[{'entity_group': 'PER',\n",
+       "  'score': 0.99884915,\n",
+       "  'word': 'Ahmad',\n",
+       "  'start': 11,\n",
+       "  'end': 16},\n",
+       " {'entity_group': 'ORG',\n",
+       "  'score': 0.9950792,\n",
+       "  'word': 'University of Engineering and Technology',\n",
+       "  'start': 31,\n",
+       "  'end': 71},\n",
+       " {'entity_group': 'LOC',\n",
+       "  'score': 0.97850055,\n",
+       "  'word': 'Lahore',\n",
+       "  'start': 73,\n",
+       "  'end': 79},\n",
+       " {'entity_group': 'ORG',\n",
+       "  'score': 0.78072757,\n",
+       "  'word': \"Bechelor ' s\",\n",
+       "  'start': 95,\n",
+       "  'end': 105},\n",
+       " {'entity_group': 'ORG',\n",
+       "  'score': 0.92247367,\n",
+       "  'word': 'Computer Science',\n",
+       "  'start': 109,\n",
+       "  'end': 125}]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "ner = pipeline(\"ner\", grouped_entities=True)\n",
+    "ner(\"My name is Ahmad and I work at University of Engineering and Technology, Lahore. I was prsuing Bechelor's of Computer Science.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Question answering"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "No model was supplied, defaulted to distilbert/distilbert-base-cased-distilled-squad and revision 564e9b5 (https://huggingface.co/distilbert/distilbert-base-cased-distilled-squad).\n",
+      "Using a pipeline without specifying a model name and revision in production is not recommended.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "question_answerer = pipeline(\"question-answering\")\n",
+    "\n",
+    "ans = question_answerer(\n",
+    "        question=\"where do I work?\",\n",
+    "        context = \"My name is Ahmad and I work at University of Engineering and Technology, Lahore\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'University of Engineering and Technology, Lahore'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ans['answer']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Summarization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "No model was supplied, defaulted to sshleifer/distilbart-cnn-12-6 and revision a4f8f3e (https://huggingface.co/sshleifer/distilbart-cnn-12-6).\n",
+      "Using a pipeline without specifying a model name and revision in production is not recommended.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "summarizer = pipeline(\"summarization\")\n",
+    "summary = summarizer(\n",
+    "    \"\"\"\n",
+    "    America has changed dramatically during recent years. Not only has the number of \n",
+    "    graduates in traditional engineering disciplines such as mechanical, civil, \n",
+    "    electrical, chemical, and aeronautical engineering declined, but in most of \n",
+    "    the premier American universities engineering curricula now concentrate on \n",
+    "    and encourage largely the study of engineering science. As a result, there \n",
+    "    are declining offerings in engineering subjects dealing with infrastructure, \n",
+    "    the environment, and related issues, and greater concentration on high \n",
+    "    technology subjects, largely supporting increasingly complex scientific \n",
+    "    developments. While the latter is important, it should not be at the expense \n",
+    "    of more traditional engineering.\n",
+    "\n",
+    "    Rapidly developing economies such as China and India, as well as other \n",
+    "    industrial countries in Europe and Asia, continue to encourage and advance \n",
+    "    the teaching of engineering. Both China and India, respectively, graduate \n",
+    "    six and eight times as many traditional engineers as does the United States. \n",
+    "    Other industrial countries at minimum maintain their output, while America \n",
+    "    suffers an increasingly serious decline in the number of engineering graduates \n",
+    "    and a lack of well-educated engineers.\n",
+    "\"\"\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " America has changed dramatically during recent years . The number of engineering graduates in the U.S. has declined in traditional engineering disciplines such as mechanical, civil,    electrical, chemical, and aeronautical engineering . Rapidly developing economies such as China and India continue to encourage and advance the teaching of engineering .\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(summary[0]['summary_text'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Translation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sentencepiece"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e7521143fb794a39b66b0f5d00f9fac8",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "source.spm:   0%|          | 0.00/802k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\ACER\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\huggingface_hub\\file_download.py:147: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\ACER\\.cache\\huggingface\\hub\\models--Helsinki-NLP--opus-mt-fr-en. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
+      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
+      "  warnings.warn(message)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d658b08296d64e4081ac272272b520d7",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "target.spm:   0%|          | 0.00/778k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "92ea52e7b8d446e7a21d844815c4045b",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "vocab.json:   0%|          | 0.00/1.34M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\ACER\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\transformers\\models\\marian\\tokenization_marian.py:175: UserWarning: Recommended: pip install sacremoses.\n",
+      "  warnings.warn(\"Recommended: pip install sacremoses.\")\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[{'translation_text': 'This course is produced by Hugging Face.'}]"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import sentencepiece\n",
+    "from transformers import pipeline\n",
+    "\n",
+    "translator = pipeline(\"translation\", model=\"Helsinki-NLP/opus-mt-fr-en\")\n",
+    "translator(\"Ce cours est produit par Hugging Face.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Bias and limitations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "BertForMaskedLM has generative capabilities, as `prepare_inputs_for_generation` is explicitly overwritten. However, it doesn't directly inherit from `GenerationMixin`. From 👉v4.50👈 onwards, `PreTrainedModel` will NOT inherit from `GenerationMixin`, and this model will lose the ability to call `generate` and other related functions.\n",
+      "  - If you're using `trust_remote_code=True`, you can get rid of this warning by loading the model with an auto class. See https://huggingface.co/docs/transformers/en/model_doc/auto#auto-classes\n",
+      "  - If you are the owner of the model architecture code, please modify your model class such that it inherits from `GenerationMixin` (after `PreTrainedModel`, otherwise you'll get an exception).\n",
+      "  - If you are not the owner of the model architecture class, please contact the model code owner to update it.\n",
+      "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForMaskedLM: ['bert.pooler.dense.bias', 'bert.pooler.dense.weight', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight']\n",
+      "- This IS expected if you are initializing BertForMaskedLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
+      "- This IS NOT expected if you are initializing BertForMaskedLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['carpenter', 'lawyer', 'farmer', 'businessman', 'doctor']\n",
+      "['nurse', 'maid', 'teacher', 'waitress', 'prostitute']\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "unmasker = pipeline(\"fill-mask\", model=\"bert-base-uncased\")\n",
+    "result = unmasker(\"This man works as a [MASK].\")\n",
+    "print([r[\"token_str\"] for r in result])\n",
+    "\n",
+    "result = unmasker(\"This woman works as a [MASK].\")\n",
+    "print([r[\"token_str\"] for r in result])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "huggingface-nlp",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

pages/1_🧠_Sentiment Analysis.py

@@ -0,0 +1,73 @@
+import torch
+import numpy as np
+import streamlit as st
+from torch.nn import Softmax
+import plotly.graph_objects as go
+from transformers import AutoConfig, AutoTokenizer
+from transformers import AutoModelForSequenceClassification
+
+
+st.set_page_config(
+    page_title="Sentiment Analysis",
+    page_icon="🧠")
+
+st.write("# Sentiment Analysis")
+
+
+MODEL = f"cardiffnlp/twitter-roberta-base-sentiment-latest"
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
+config = AutoConfig.from_pretrained(MODEL)
+model = AutoModelForSequenceClassification.from_pretrained(MODEL)
+
+user_input = st.text_input('What\'s in your mind?')
+
+if st.button("Perform Sentiment Analysis"):
+    if not user_input:
+        st.warning("Please enter some text!")
+    else:
+        try:
+            st.write("## Sentiment Plot")
+            encoded_input = tokenizer(user_input, return_tensors='pt')
+            output = model(**encoded_input)
+            scores = output[0][0].detach().numpy()
+            softmax = Softmax(dim=1)
+            scores = softmax(torch.tensor([scores]))
+            scores = scores.numpy()[0]
+
+            categories = []
+            probabilities = []
+            ranking = np.argsort(scores)
+            ranking = ranking[::-1]
+            for i in range(scores.shape[0]):
+                categories.append(config.id2label[ranking[i]])
+                probabilities.append(np.round(float(scores[ranking[i]]), 4).tolist())
+
+            res = [[cat, sco] for cat,sco in zip(categories, probabilities)]
+            res.sort(key=lambda x: x[0], reverse=True)
+            probabilities = [i[1] for i in res]
+
+
+            # Create the bar chart
+            fig = go.Figure(data=[
+                go.Bar(
+                    x=['Positive', 'Neutral', 'Negative'], 
+                    y=probabilities, 
+                    marker_color=['green', 'blue', 'red'],  # Colors for each category
+                    text=probabilities,  # Show values on the bars
+                    textposition='auto'
+                )
+            ])
+
+            # Customize layout
+            fig.update_layout(
+                # title="Sentiment Analysis Results",
+                xaxis_title="Sentiment Categories",
+                yaxis_title="Probability",
+                template="plotly_white"
+            )
+
+            # Show the figure
+
+            st.plotly_chart(fig, use_container_width=True)
+        except Exception as e:
+            st.error("An error occurred: " + str(e))

pages/2_📝_Fill Mask.py

@@ -0,0 +1,31 @@
+import torch
+import streamlit as st
+from transformers import pipeline
+
+st.set_page_config(
+    page_title="Fill Mask",
+    page_icon="📝")
+
+st.write("# Fill Mask")
+unmasker = pipeline('fill-mask', model='bert-base-uncased')
+
+st.write("Enter a sentence with a masked word using `[MASK]`.")
+user_input = st.text_input("Input your sentence:", "The capital of France is [MASK].")
+
+num_responses = st.slider("Select the number of predictions:", min_value=1, max_value=20, value=5)
+
+if st.button("Generate Predictions"):
+    if "[MASK]" not in user_input:
+        st.error("Please include '[MASK]' in your input sentence.")
+    else:
+        try:
+            st.write("### Predictions:")
+            predictions = unmasker(user_input, top_k=num_responses)
+            for i, prediction in enumerate(predictions):
+                token = prediction['token_str']
+                score = prediction['score']
+                user_input_before,user_input_after = user_input.split("[MASK]")
+                user_input_with_token = user_input_before + "`" + token + "`"+ user_input_after
+                st.write(user_input_with_token)
+        except Exception as e:
+            st.error(f"An error occurred: {e}")

pages/3_🚀_Zero Shot Classification.py

@@ -0,0 +1,84 @@
+import numpy as np
+import streamlit as st
+import plotly.graph_objects as go
+from transformers import pipeline
+
+st.set_page_config(
+    page_title="Fill Mask",
+    page_icon="🚀")
+
+# App Title
+st.title("Zero-Shot Text Classification")
+
+# Initialize the zero-shot classification pipeline
+zero_shot = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+
+# Colors
+colors = ['rgba(24, 203, 162, 1)', 'rgba(34, 180, 20, 1)', 'rgba(231, 110, 212, 1)', 'rgba(191, 206, 164, 1)', 'rgba(100, 233, 42, 1)', 
+    'rgba(185, 222, 92, 1)', 'rgba(27, 157, 138, 1)', 'rgba(212, 207, 155, 1)', 'rgba(172, 202, 164, 1)', 'rgba(47, 65, 177, 1)', 
+    'rgba(26, 44, 233, 1)', 'rgba(65, 242, 9, 1)', 'rgba(171, 50, 253, 1)', 'rgba(125, 201, 227, 1)', 'rgba(135, 196, 15, 1)', 
+    'rgba(114, 106, 242, 1)', 'rgba(176, 50, 34, 1)', 'rgba(100, 159, 247, 1)', 'rgba(246, 103, 72, 1)', 'rgba(180, 180, 5, 1)', 
+    'rgba(64, 29, 164, 1)', 'rgba(65, 192, 5, 1)', 'rgba(149, 97, 155, 1)', 'rgba(210, 2, 107, 1)', 'rgba(70, 203, 162, 1)', 
+    'rgba(68, 74, 64, 1)', 'rgba(164, 42, 173, 1)', 'rgba(220, 37, 239, 1)', 'rgba(76, 89, 84, 1)', 'rgba(29, 190, 84, 1)', 
+    'rgba(180, 35, 240, 1)', 'rgba(222, 72, 217, 1)', 'rgba(203, 80, 243, 1)', 'rgba(121, 164, 68, 1)', 'rgba(107, 218, 79, 1)', 
+    'rgba(152, 225, 65, 1)', 'rgba(57, 170, 43, 1)', 'rgba(77, 131, 61, 1)', 'rgba(145, 101, 161, 1)', 'rgba(115, 77, 3, 1)', 
+    'rgba(29, 159, 63, 1)', 'rgba(71, 105, 200, 1)', 'rgba(98, 78, 55, 1)', 'rgba(242, 159, 60, 1)', 'rgba(175, 67, 54, 1)', 
+    'rgba(120, 246, 81, 1)', 'rgba(216, 132, 219, 1)', 'rgba(82, 77, 251, 1)', 'rgba(213, 29, 120, 1)', 'rgba(252, 90, 31, 1)', 
+    'rgba(194, 181, 168, 1)', 'rgba(246, 60, 189, 1)', 'rgba(22, 50, 26, 1)', 'rgba(54, 11, 134, 1)', 'rgba(27, 103, 59, 1)', 
+    'rgba(234, 96, 187, 1)', 'rgba(167, 157, 215, 1)', 'rgba(104, 1, 252, 1)', 'rgba(76, 121, 131, 1)', 'rgba(65, 250, 218, 1)', 
+    'rgba(219, 59, 127, 1)', 'rgba(18, 242, 194, 1)', 'rgba(14, 132, 131, 1)', 'rgba(82, 68, 61, 1)', 'rgba(109, 229, 43, 1)', 
+    'rgba(202, 96, 66, 1)', 'rgba(216, 112, 64, 1)', 'rgba(101, 215, 114, 1)', 'rgba(85, 234, 109, 1)', 'rgba(17, 43, 113, 1)', 
+    'rgba(104, 132, 5, 1)', 'rgba(23, 177, 214, 1)', 'rgba(112, 131, 160, 1)', 'rgba(142, 43, 188, 1)', 'rgba(189, 61, 176, 1)', 
+    'rgba(196, 198, 61, 1)', 'rgba(253, 176, 165, 1)', 'rgba(113, 143, 126, 1)', 'rgba(122, 156, 220, 1)', 'rgba(221, 11, 29, 1)', 
+    'rgba(233, 200, 5, 1)', 'rgba(232, 176, 217, 1)', 'rgba(199, 6, 130, 1)', 'rgba(140, 118, 154, 1)', 'rgba(177, 46, 36, 1)', 
+    'rgba(244, 81, 66, 1)', 'rgba(94, 99, 24, 1)', 'rgba(159, 90, 50, 1)', 'rgba(67, 144, 236, 1)', 'rgba(78, 202, 143, 1)', 
+    'rgba(13, 116, 114, 1)', 'rgba(139, 194, 124, 1)', 'rgba(174, 63, 214, 1)', 'rgba(84, 114, 130, 1)', 'rgba(143, 208, 199, 1)', 
+    'rgba(27, 60, 225, 1)', 'rgba(69, 228, 28, 1)', 'rgba(167, 157, 10, 1)', 'rgba(61, 185, 55, 1)', 'rgba(143, 52, 233, 1)']
+
+colors = np.array(colors)
+
+# Input Section
+st.write("Enter a sentence or text to classify and provide possible labels.")
+
+user_input = st.text_input("Input your text:", "Streamlit is an amazing tool for building web apps.")
+labels_input = st.text_input("Enter possible labels (comma-separated):", "technology, finance, health")
+
+# Process and Display Results
+if st.button("Classify Text"):
+    labels = [label.strip().title() for label in labels_input.split(",") if label.strip()]
+    if not user_input or not labels:
+        st.error("Please provide both text and at least one label.")
+    else:
+        try:
+            st.write("## Classification Results:")
+            probabilities = []
+            result = zero_shot(user_input, labels)
+
+            for label, score in zip(result['labels'], result['scores']):
+                probabilities.append(round(score, 2))
+            
+            fig = go.Figure(data=[
+            go.Bar(
+                x=labels, 
+                y=probabilities, 
+                marker_color=np.random.choice(colors, len(labels)).tolist(),  # Colors for each category
+                text=probabilities,  # Show values on the bars
+                textposition='auto'
+            )
+        ])
+
+        # Customize layout
+            fig.update_layout(
+                # title="Sentiment Analysis Results",
+                xaxis_title="Label",
+                yaxis_title="Probability",
+                template="seaborn",
+            )
+
+            # Show the figure
+
+            st.plotly_chart(fig, use_container_width=True, theme=None)
+
+        except Exception as e:
+                st.error(f"An error occurred: {e}")
+            

pages/4_❓_Question Answer.py

@@ -0,0 +1,31 @@
+import streamlit as st
+from transformers import pipeline
+
+
+st.set_page_config(
+    page_title="Question Answer",
+    page_icon="❓")
+
+# App Name
+st.write("# Question Answer")
+
+# Model
+qa_model = pipeline("question-answering", model="distilbert/distilbert-base-cased-distilled-squad")
+
+
+st.write("Provide context and question.")
+
+question = st.text_input("Enter your question:")
+context = st.text_input("Enter the context:")
+
+if st.button("Generate Answer"):
+    if not (question or context):
+        st.warning("Provide both question and context.")
+    else:
+        try:
+            st.write("## Answer")
+            ans = qa_model(question=question, context=context)
+            st.write(ans['answer'])
+        except Exception as e:
+            st.error(f"An error occurred: {e}")
+            

pages/5_✍️_Text_Summarization.py

@@ -0,0 +1,22 @@
+import streamlit as st
+from transformers import pipeline
+
+
+st.set_page_config(
+    page_title="Question Answer",
+    page_icon="✍️")
+
+st.write("# Text Summarization")
+
+# Model
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+
+user_input = st.text_area("Enter text to summarize")
+
+if st.button("Generate Predictions"):
+        try:
+            st.write("## Summary:")
+            generated_summary = summarizer(user_input)
+            st.write(generated_summary[0]["summary_text"])
+        except Exception as e:
+            st.error(f"An error occurred: {e}")

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+streamlit
+torch
+plotly

🏠_Home.py

@@ -0,0 +1,30 @@
+import torch
+import streamlit as st
+from transformers import pipeline
+
+st.set_page_config(
+    page_title="Transformers in Action",
+    page_icon="🏠",
+)
+
+st.sidebar.success("Select a Demo above.")
+
+st.markdown(
+    """
+    # **Transformers in Action**  
+    **Welcome to the Future of AI!**
+
+    Discover the incredible power of modern **Transformer models** and how they can revolutionize the way you approach everyday tasks. Whether you want to analyze sentiment, fill in missing text, or classify data with zero-shot precision, this interactive app provides a seamless playground to explore Hugging Face models in action.
+
+    ### **What Can You Do Here?**  
+    🧠 **Sentiment Analysis** - Understand emotions in text, from happiness to frustration.  
+    📝 **Fill Mask** - Predict missing words with precision using intelligent language models.  
+    🚀 **Zero-Shot Classification** - Classify text into categories without pre-training.  
+    ❓ **Question Answering** - Get instant answers to your queries with context-aware AI.  
+    ✍️ **Text Summarization** - Condense lengthy content into concise summaries.  
+
+    **Ready to experience the magic of AI?**  
+    Pick a task from the left, explore, and bring your ideas to life!  
+
+    """
+)