Added the model file and tokenizer as a directory

albert/.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,201 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "8804bc60-c9e2-4713-9800-1bc2fea11241",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/umesh/conda/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "322cd68e-9257-4d07-aafc-19e9072f1bba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import AutoModelForSequenceClassification, AutoTokenizer\n",
+    "\n",
+    "model = AutoModelForSequenceClassification.from_pretrained('.')\n",
+    "tokenizer = AutoTokenizer.from_pretrained('.')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "fde22c8f-4d57-4544-bc2b-55e4dbbc5fd3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "classifier = pipeline('sentiment-analysis',model = model, tokenizer = tokenizer, top_k =1)\n",
+    "det_classer = pipeline('sentiment-analysis',model = model, tokenizer = tokenizer, top_k =None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "087c3506-5d27-4dd6-9377-fb34e6926698",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "inputs=['This is a rather confusing statement','I do not want to bee seen with you Kusakabe','Rin chan was elegant in dismissing your favours','Damn you! Bonn-kun']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "f5683415-239a-4e68-8f4c-1b9ba8295787",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[[{'label': 'DISGUST', 'score': 0.2899283468723297}],\n",
+       " [{'label': 'DISGUST', 'score': 0.20709046721458435}],\n",
+       " [{'label': 'OPTIMISM', 'score': 0.1878553181886673}],\n",
+       " [{'label': 'ANGER', 'score': 0.46816307306289673}]]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "classifier(inputs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "9b45cd86-cd63-40b1-81ff-7b510ac94c8d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "statement='Today I did not finish my project and stayed silently away from meetings but my boss found it out and shouted at me in front of a female colleague '"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "a7361b72-d959-4993-80cf-5c0d65f3e703",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def classify (statement):\n",
+    "    preds = det_classer(statement)\n",
+    "    return {label}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "9b6bff6a-3a70-48d8-8b03-1d8327278cad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import gradio as gr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "d1aa90b3-678f-4ae0-bfa7-6018034c5b3e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7860\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7860/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Traceback (most recent call last):\n",
+      "  File \"/home/umesh/conda/lib/python3.10/site-packages/gradio/queueing.py\", line 527, in process_events\n",
+      "    response = await route_utils.call_process_api(\n",
+      "  File \"/home/umesh/conda/lib/python3.10/site-packages/gradio/route_utils.py\", line 261, in call_process_api\n",
+      "    output = await app.get_blocks().process_api(\n",
+      "  File \"/home/umesh/conda/lib/python3.10/site-packages/gradio/blocks.py\", line 1795, in process_api\n",
+      "    data = await self.postprocess_data(fn_index, result[\"prediction\"], state)\n",
+      "  File \"/home/umesh/conda/lib/python3.10/site-packages/gradio/blocks.py\", line 1623, in postprocess_data\n",
+      "    prediction_value = block.postprocess(prediction_value)\n",
+      "  File \"/home/umesh/conda/lib/python3.10/site-packages/gradio/components/label.py\", line 137, in postprocess\n",
+      "    raise ValueError(\n",
+      "ValueError: The `Label` output interface expects one of: a string label, or an int label, a float label, or a dictionary whose keys are labels and values are confidences. Instead, got a <class 'list'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "demo = gr.Interface(fn=classify, inputs='text',outputs=gr.Label())\n",
+    "demo.launch()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e7852458-9afc-4443-bfc8-ebd16909dc6a",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

albert/.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "albert/albert-base-v2",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

albert/Untitled.ipynb

@@ -0,0 +1,246 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8804bc60-c9e2-4713-9800-1bc2fea11241",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/umesh/conda/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "322cd68e-9257-4d07-aafc-19e9072f1bba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import AutoModelForSequenceClassification, AutoTokenizer\n",
+    "\n",
+    "model = AutoModelForSequenceClassification.from_pretrained('.')\n",
+    "tokenizer = AutoTokenizer.from_pretrained('.')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "fde22c8f-4d57-4544-bc2b-55e4dbbc5fd3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "classifier = pipeline('sentiment-analysis',model = model, tokenizer = tokenizer, top_k =1)\n",
+    "det_classer = pipeline('sentiment-analysis',model = model, tokenizer = tokenizer, top_k =None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "087c3506-5d27-4dd6-9377-fb34e6926698",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "inputs=['This is a rather confusing statement','I do not want to bee seen with you Kusakabe','Rin chan was elegant in dismissing your favours','Damn you! Bonn-kun']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "f5683415-239a-4e68-8f4c-1b9ba8295787",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[[{'label': 'DISGUST', 'score': 0.2899283468723297}],\n",
+       " [{'label': 'DISGUST', 'score': 0.20709046721458435}],\n",
+       " [{'label': 'OPTIMISM', 'score': 0.1878553181886673}],\n",
+       " [{'label': 'ANGER', 'score': 0.46816307306289673}]]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "classifier(inputs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "9b45cd86-cd63-40b1-81ff-7b510ac94c8d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "statement='Today I did not finish my project and stayed silently away from meetings but my boss found it out and shouted at me in front of a female colleague '"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "3ae20452-e327-4550-a40d-f28280aad3c8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x = det_classer(statement)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ba091f5c-b98c-49ee-a361-f8937c3693c1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'DISGUST'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x[0][0]['label']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "003693e3-1aac-4d67-9c54-f17bcda1af34",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'DISGUST': 0.3289419114589691}\n",
+      "{'ANGER': 0.2868015170097351}\n",
+      "{'SADNESS': 0.12498752772808075}\n",
+      "{'FEAR': 0.09882446378469467}\n",
+      "{'ANTICIPATION': 0.051536574959754944}\n",
+      "{'JOY': 0.03244535252451897}\n",
+      "{'SURPRISE': 0.023728473111987114}\n",
+      "{'PESSIMISM': 0.020501434803009033}\n",
+      "{'OPTIMISM': 0.020457664504647255}\n",
+      "{'COMPLICATED': 0.006496347486972809}\n",
+      "{'TRUST': 0.0026527740992605686}\n",
+      "{'LOVE': 0.0026260693557560444}\n"
+     ]
+    }
+   ],
+   "source": [
+    "for a in x[0]:\n",
+    "    print ({a['label']:a['score']})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "a7361b72-d959-4993-80cf-5c0d65f3e703",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def classify (statement):\n",
+    "    preds = det_classer(statement)\n",
+    "    return {i['label']:float(i['score']) for i in preds[0]}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "9b6bff6a-3a70-48d8-8b03-1d8327278cad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import gradio as gr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "d1aa90b3-678f-4ae0-bfa7-6018034c5b3e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7862\n",
+      "IMPORTANT: You are using gradio version 4.26.0, however version 4.29.0 is available, please upgrade.\n",
+      "--------\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7862/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "demo = gr.Interface(fn=classify, inputs='text',outputs=gr.Label())\n",
+    "demo.launch()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e7852458-9afc-4443-bfc8-ebd16909dc6a",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

albert/config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "albert/albert-base-v2",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ANGER",
+    "1": "ANTICIPATION",
+    "2": "DISGUST",
+    "3": "FEAR",
+    "4": "JOY",
+    "5": "LOVE",
+    "6": "OPTIMISM",
+    "7": "PESSIMISM",
+    "8": "SADNESS",
+    "9": "SURPRISE",
+    "10": "TRUST",
+    "11": "COMPLICATED"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ANGER": 0,
+    "ANTICIPATION": 1,
+    "TRUST": 10,
+    "COMPLICATED": 11,
+    "DISGUST": 2,
+    "FEAR": 3,
+    "JOY": 4,
+    "LOVE": 5,
+    "OPTIMISM": 6,
+    "PESSIMISM": 7,
+    "SADNESS": 8,
+    "SURPRISE": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

albert/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e43e075ab873a63c42e79634ea3cdf7e4b83220e5dec7bd740491e0d9ade4de
+size 46774672

albert/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

albert/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

albert/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

albert/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7953cea3ce73edf986db65195dfbaf85c6bd32338ed9940384c4e150b443847a
+size 4984