Upload 9 files

added_tokens.json

@@ -0,0 +1,102 @@
+{
+  "<extra_id_0>": 32099,
+  "<extra_id_10>": 32089,
+  "<extra_id_11>": 32088,
+  "<extra_id_12>": 32087,
+  "<extra_id_13>": 32086,
+  "<extra_id_14>": 32085,
+  "<extra_id_15>": 32084,
+  "<extra_id_16>": 32083,
+  "<extra_id_17>": 32082,
+  "<extra_id_18>": 32081,
+  "<extra_id_19>": 32080,
+  "<extra_id_1>": 32098,
+  "<extra_id_20>": 32079,
+  "<extra_id_21>": 32078,
+  "<extra_id_22>": 32077,
+  "<extra_id_23>": 32076,
+  "<extra_id_24>": 32075,
+  "<extra_id_25>": 32074,
+  "<extra_id_26>": 32073,
+  "<extra_id_27>": 32072,
+  "<extra_id_28>": 32071,
+  "<extra_id_29>": 32070,
+  "<extra_id_2>": 32097,
+  "<extra_id_30>": 32069,
+  "<extra_id_31>": 32068,
+  "<extra_id_32>": 32067,
+  "<extra_id_33>": 32066,
+  "<extra_id_34>": 32065,
+  "<extra_id_35>": 32064,
+  "<extra_id_36>": 32063,
+  "<extra_id_37>": 32062,
+  "<extra_id_38>": 32061,
+  "<extra_id_39>": 32060,
+  "<extra_id_3>": 32096,
+  "<extra_id_40>": 32059,
+  "<extra_id_41>": 32058,
+  "<extra_id_42>": 32057,
+  "<extra_id_43>": 32056,
+  "<extra_id_44>": 32055,
+  "<extra_id_45>": 32054,
+  "<extra_id_46>": 32053,
+  "<extra_id_47>": 32052,
+  "<extra_id_48>": 32051,
+  "<extra_id_49>": 32050,
+  "<extra_id_4>": 32095,
+  "<extra_id_50>": 32049,
+  "<extra_id_51>": 32048,
+  "<extra_id_52>": 32047,
+  "<extra_id_53>": 32046,
+  "<extra_id_54>": 32045,
+  "<extra_id_55>": 32044,
+  "<extra_id_56>": 32043,
+  "<extra_id_57>": 32042,
+  "<extra_id_58>": 32041,
+  "<extra_id_59>": 32040,
+  "<extra_id_5>": 32094,
+  "<extra_id_60>": 32039,
+  "<extra_id_61>": 32038,
+  "<extra_id_62>": 32037,
+  "<extra_id_63>": 32036,
+  "<extra_id_64>": 32035,
+  "<extra_id_65>": 32034,
+  "<extra_id_66>": 32033,
+  "<extra_id_67>": 32032,
+  "<extra_id_68>": 32031,
+  "<extra_id_69>": 32030,
+  "<extra_id_6>": 32093,
+  "<extra_id_70>": 32029,
+  "<extra_id_71>": 32028,
+  "<extra_id_72>": 32027,
+  "<extra_id_73>": 32026,
+  "<extra_id_74>": 32025,
+  "<extra_id_75>": 32024,
+  "<extra_id_76>": 32023,
+  "<extra_id_77>": 32022,
+  "<extra_id_78>": 32021,
+  "<extra_id_79>": 32020,
+  "<extra_id_7>": 32092,
+  "<extra_id_80>": 32019,
+  "<extra_id_81>": 32018,
+  "<extra_id_82>": 32017,
+  "<extra_id_83>": 32016,
+  "<extra_id_84>": 32015,
+  "<extra_id_85>": 32014,
+  "<extra_id_86>": 32013,
+  "<extra_id_87>": 32012,
+  "<extra_id_88>": 32011,
+  "<extra_id_89>": 32010,
+  "<extra_id_8>": 32091,
+  "<extra_id_90>": 32009,
+  "<extra_id_91>": 32008,
+  "<extra_id_92>": 32007,
+  "<extra_id_93>": 32006,
+  "<extra_id_94>": 32005,
+  "<extra_id_95>": 32004,
+  "<extra_id_96>": 32003,
+  "<extra_id_97>": 32002,
+  "<extra_id_98>": 32001,
+  "<extra_id_99>": 32000,
+  "<extra_id_9>": 32090
+}

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

grammar-correction.ipynb

@@ -0,0 +1 @@
+{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[],"dockerImageVersionId":31011,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:02:33.337082Z","iopub.execute_input":"2025-05-12T07:02:33.337470Z","iopub.status.idle":"2025-05-12T07:02:36.330361Z","shell.execute_reply.started":"2025-05-12T07:02:33.337449Z","shell.execute_reply":"2025-05-12T07:02:36.329585Z"}},"outputs":[],"execution_count":1},{"cell_type":"code","source":"import os\nos.environ[\"WANDB_DISABLED\"] = \"true\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:02:36.331243Z","iopub.execute_input":"2025-05-12T07:02:36.331630Z","iopub.status.idle":"2025-05-12T07:02:36.335178Z","shell.execute_reply.started":"2025-05-12T07:02:36.331588Z","shell.execute_reply":"2025-05-12T07:02:36.334472Z"}},"outputs":[],"execution_count":2},{"cell_type":"code","source":"from datasets import load_dataset, Dataset\nimport pandas as pd\n\n# Load JFLEG dataset\ndataset = load_dataset(\"jfleg\")\ndata = dataset[\"test\"]  # JFLEG only has a test split\n\n# Use first reference for each sentence\ninputs = [f\"fix: {item['sentence']}\" for item in data]  # Prompt-style input\ntargets = [item[\"corrections\"][0] for item in data]\n\n# Create DataFrame and convert to Dataset\ndf = pd.DataFrame({\"input\": inputs, \"target\": targets})\ndf = df[df[\"input\"].str.strip() != \"\"]\nhf_dataset = Dataset.from_pandas(df)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:02:36.336908Z","iopub.execute_input":"2025-05-12T07:02:36.337150Z","iopub.status.idle":"2025-05-12T07:02:42.256354Z","shell.execute_reply.started":"2025-05-12T07:02:36.337128Z","shell.execute_reply":"2025-05-12T07:02:42.255577Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"README.md:   0%|          | 0.00/5.94k [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"458b5420fefd4daa944f179ddf6deb2e"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"validation-00000-of-00001.parquet:   0%|          | 0.00/148k [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"f692d45f984d444ea9e9703a9e427e4b"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"test-00000-of-00001.parquet:   0%|          | 0.00/141k [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"53ad19277ce645bfbf57754a1b3af49d"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"Generating validation split:   0%|          | 0/755 [00:00<?, ? examples/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"bf55809fccc243efafe33862cdc214d2"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"Generating test split:   0%|          | 0/748 [00:00<?, ? examples/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"24bdcb7d7cec442aac610eaa0cd1fc66"}},"metadata":{}}],"execution_count":3},{"cell_type":"code","source":"import torch\ndevice = 'cuda' if torch.cuda.is_available() else 'cpu'\n\nfrom transformers import T5Tokenizer, T5ForConditionalGeneration\n\ntokenizer = T5Tokenizer.from_pretrained(\"t5-base\")\nmodel = T5ForConditionalGeneration.from_pretrained(\"t5-base\").to(device)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:02:42.257238Z","iopub.execute_input":"2025-05-12T07:02:42.257750Z","iopub.status.idle":"2025-05-12T07:03:25.053806Z","shell.execute_reply.started":"2025-05-12T07:02:42.257723Z","shell.execute_reply":"2025-05-12T07:03:25.052999Z"}},"outputs":[{"name":"stderr","text":"2025-05-12 07:03:03.792581: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\nWARNING: All log messages before absl::InitializeLog() is called are written to STDERR\nE0000 00:00:1747033384.246811      31 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\nE0000 00:00:1747033384.366400      31 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"spiece.model:   0%|          | 0.00/792k [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"ce268734b0a74c29981b8b09b645d6eb"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"tokenizer.json:   0%|          | 0.00/1.39M [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"27385643d60b41159d1c4a3654ed20d1"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"config.json:   0%|          | 0.00/1.21k [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"0cc2cca685324b51b4e86537a7c82ff0"}},"metadata":{}},{"name":"stderr","text":"You are using the default legacy behaviour of the <class 'transformers.models.t5.tokenization_t5.T5Tokenizer'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565\nXet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"model.safetensors:   0%|          | 0.00/892M [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"8e13ea6a11c5402d9c8cd11c24beb808"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"generation_config.json:   0%|          | 0.00/147 [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"711d6a138e92483db535f2386939619f"}},"metadata":{}}],"execution_count":4},{"cell_type":"code","source":"# Preprocess function\ndef preprocess_function(example):\n    model_inputs = tokenizer(example[\"input\"], max_length=128, truncation=True, padding=\"max_length\")\n    labels = tokenizer(example[\"target\"], max_length=128, truncation=True, padding=\"max_length\")\n    model_inputs[\"labels\"] = labels[\"input_ids\"]\n    return model_inputs\n\n# Tokenize dataset\ntokenized_dataset = hf_dataset.map(preprocess_function, batched=True)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:03:25.054705Z","iopub.execute_input":"2025-05-12T07:03:25.055258Z","iopub.status.idle":"2025-05-12T07:03:25.333883Z","shell.execute_reply.started":"2025-05-12T07:03:25.055237Z","shell.execute_reply":"2025-05-12T07:03:25.332836Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"Map:   0%|          | 0/748 [00:00<?, ? examples/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"fac88ca9cc8143838d9da07a608e1dee"}},"metadata":{}}],"execution_count":5},{"cell_type":"code","source":"from transformers import Seq2SeqTrainingArguments, Seq2SeqTrainer\n\ntraining_args = Seq2SeqTrainingArguments(\n    output_dir=\"./t5-grammar-jfleg\",\n    eval_strategy=\"epoch\",\n    save_strategy=\"epoch\",\n    learning_rate=3e-4,\n    per_device_train_batch_size=8,\n    per_device_eval_batch_size=8,\n    weight_decay=0.01,\n    num_train_epochs=5,\n    predict_with_generate=True,\n    logging_dir=\"./logs\",\n    logging_steps=50,\n    save_total_limit=2,\n    load_best_model_at_end=True,\n    metric_for_best_model=\"eval_loss\"\n)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:03:25.334871Z","iopub.execute_input":"2025-05-12T07:03:25.335093Z","iopub.status.idle":"2025-05-12T07:03:27.623202Z","shell.execute_reply.started":"2025-05-12T07:03:25.335075Z","shell.execute_reply":"2025-05-12T07:03:27.622502Z"}},"outputs":[{"name":"stderr","text":"Using the `WANDB_DISABLED` environment variable is deprecated and will be removed in v5. Use the --report_to flag to control the integrations used for logging result (for instance --report_to none).\n","output_type":"stream"}],"execution_count":6},{"cell_type":"code","source":"!pip install evaluate","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:03:27.623958Z","iopub.execute_input":"2025-05-12T07:03:27.624236Z","iopub.status.idle":"2025-05-12T07:03:37.303756Z","shell.execute_reply.started":"2025-05-12T07:03:27.624211Z","shell.execute_reply":"2025-05-12T07:03:37.303013Z"}},"outputs":[{"name":"stdout","text":"Collecting evaluate\n  Downloading evaluate-0.4.3-py3-none-any.whl.metadata (9.2 kB)\nRequirement already satisfied: datasets>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from evaluate) (3.5.0)\nRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/dist-packages (from evaluate) (1.26.4)\nRequirement already satisfied: dill in /usr/local/lib/python3.11/dist-packages (from evaluate) (0.3.8)\nRequirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from evaluate) (2.2.3)\nRequirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.11/dist-packages (from evaluate) (2.32.3)\nRequirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.11/dist-packages (from evaluate) (4.67.1)\nRequirement already satisfied: xxhash in /usr/local/lib/python3.11/dist-packages (from evaluate) (3.5.0)\nRequirement already satisfied: multiprocess in /usr/local/lib/python3.11/dist-packages (from evaluate) (0.70.16)\nRequirement already satisfied: fsspec>=2021.05.0 in /usr/local/lib/python3.11/dist-packages (from fsspec[http]>=2021.05.0->evaluate) (2025.3.2)\nRequirement already satisfied: huggingface-hub>=0.7.0 in /usr/local/lib/python3.11/dist-packages (from evaluate) (0.30.2)\nRequirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from evaluate) (24.2)\nRequirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from datasets>=2.0.0->evaluate) (3.18.0)\nRequirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.0.0->evaluate) (19.0.1)\nCollecting fsspec>=2021.05.0 (from fsspec[http]>=2021.05.0->evaluate)\n  Downloading fsspec-2024.12.0-py3-none-any.whl.metadata (11 kB)\nRequirement already satisfied: aiohttp in /usr/local/lib/python3.11/dist-packages (from datasets>=2.0.0->evaluate) (3.11.16)\nRequirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.0.0->evaluate) (6.0.2)\nRequirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.7.0->evaluate) (4.13.1)\nRequirement already satisfied: mkl_fft in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->evaluate) (1.3.8)\nRequirement already satisfied: mkl_random in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->evaluate) (1.2.4)\nRequirement already satisfied: mkl_umath in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->evaluate) (0.1.1)\nRequirement already satisfied: mkl in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->evaluate) (2025.1.0)\nRequirement already satisfied: tbb4py in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->evaluate) (2022.1.0)\nRequirement already satisfied: mkl-service in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->evaluate) (2.4.1)\nRequirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests>=2.19.0->evaluate) (3.4.1)\nRequirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests>=2.19.0->evaluate) (3.10)\nRequirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests>=2.19.0->evaluate) (2.3.0)\nRequirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests>=2.19.0->evaluate) (2025.1.31)\nRequirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas->evaluate) (2.9.0.post0)\nRequirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas->evaluate) (2025.2)\nRequirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas->evaluate) (2025.2)\nRequirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (2.6.1)\nRequirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.3.2)\nRequirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (25.3.0)\nRequirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.5.0)\nRequirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (6.2.0)\nRequirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (0.3.1)\nRequirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.19.0)\nRequirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas->evaluate) (1.17.0)\nRequirement already satisfied: intel-openmp<2026,>=2024 in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.17->evaluate) (2024.2.0)\nRequirement already satisfied: tbb==2022.* in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.17->evaluate) (2022.1.0)\nRequirement already satisfied: tcmlib==1.* in /usr/local/lib/python3.11/dist-packages (from tbb==2022.*->mkl->numpy>=1.17->evaluate) (1.2.0)\nRequirement already satisfied: intel-cmplr-lib-rt in /usr/local/lib/python3.11/dist-packages (from mkl_umath->numpy>=1.17->evaluate) (2024.2.0)\nRequirement already satisfied: intel-cmplr-lib-ur==2024.2.0 in /usr/local/lib/python3.11/dist-packages (from intel-openmp<2026,>=2024->mkl->numpy>=1.17->evaluate) (2024.2.0)\nDownloading evaluate-0.4.3-py3-none-any.whl (84 kB)\n\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.0/84.0 kB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading fsspec-2024.12.0-py3-none-any.whl (183 kB)\n\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m183.9/183.9 kB\u001b[0m \u001b[31m5.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hInstalling collected packages: fsspec, evaluate\n  Attempting uninstall: fsspec\n    Found existing installation: fsspec 2025.3.2\n    Uninstalling fsspec-2025.3.2:\n      Successfully uninstalled fsspec-2025.3.2\n\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\ngcsfs 2024.10.0 requires fsspec==2024.10.0, but you have fsspec 2024.12.0 which is incompatible.\ntorch 2.5.1+cu124 requires nvidia-cublas-cu12==12.4.5.8; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-cublas-cu12 12.8.4.1 which is incompatible.\ntorch 2.5.1+cu124 requires nvidia-cudnn-cu12==9.1.0.70; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-cudnn-cu12 9.3.0.75 which is incompatible.\ntorch 2.5.1+cu124 requires nvidia-cufft-cu12==11.2.1.3; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-cufft-cu12 11.3.3.83 which is incompatible.\ntorch 2.5.1+cu124 requires nvidia-curand-cu12==10.3.5.147; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-curand-cu12 10.3.9.90 which is incompatible.\ntorch 2.5.1+cu124 requires nvidia-cusolver-cu12==11.6.1.9; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-cusolver-cu12 11.7.3.90 which is incompatible.\ntorch 2.5.1+cu124 requires nvidia-cusparse-cu12==12.3.1.170; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-cusparse-cu12 12.5.8.93 which is incompatible.\ntorch 2.5.1+cu124 requires nvidia-nvjitlink-cu12==12.4.127; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-nvjitlink-cu12 12.8.93 which is incompatible.\nbigframes 1.36.0 requires rich<14,>=12.4.4, but you have rich 14.0.0 which is incompatible.\u001b[0m\u001b[31m\n\u001b[0mSuccessfully installed evaluate-0.4.3 fsspec-2024.12.0\n","output_type":"stream"}],"execution_count":7},{"cell_type":"code","source":"!pip install sacrebleu","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:03:37.304686Z","iopub.execute_input":"2025-05-12T07:03:37.304896Z","iopub.status.idle":"2025-05-12T07:03:40.733951Z","shell.execute_reply.started":"2025-05-12T07:03:37.304874Z","shell.execute_reply":"2025-05-12T07:03:40.733234Z"}},"outputs":[{"name":"stdout","text":"Collecting sacrebleu\n  Downloading sacrebleu-2.5.1-py3-none-any.whl.metadata (51 kB)\n\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m51.8/51.8 kB\u001b[0m \u001b[31m1.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hCollecting portalocker (from sacrebleu)\n  Downloading portalocker-3.1.1-py3-none-any.whl.metadata (8.6 kB)\nRequirement already satisfied: regex in /usr/local/lib/python3.11/dist-packages (from sacrebleu) (2024.11.6)\nRequirement already satisfied: tabulate>=0.8.9 in /usr/local/lib/python3.11/dist-packages (from sacrebleu) (0.9.0)\nRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/dist-packages (from sacrebleu) (1.26.4)\nRequirement already satisfied: colorama in /usr/local/lib/python3.11/dist-packages (from sacrebleu) (0.4.6)\nRequirement already satisfied: lxml in /usr/local/lib/python3.11/dist-packages (from sacrebleu) (5.3.1)\nRequirement already satisfied: mkl_fft in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->sacrebleu) (1.3.8)\nRequirement already satisfied: mkl_random in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->sacrebleu) (1.2.4)\nRequirement already satisfied: mkl_umath in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->sacrebleu) (0.1.1)\nRequirement already satisfied: mkl in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->sacrebleu) (2025.1.0)\nRequirement already satisfied: tbb4py in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->sacrebleu) (2022.1.0)\nRequirement already satisfied: mkl-service in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->sacrebleu) (2.4.1)\nRequirement already satisfied: intel-openmp<2026,>=2024 in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.17->sacrebleu) (2024.2.0)\nRequirement already satisfied: tbb==2022.* in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.17->sacrebleu) (2022.1.0)\nRequirement already satisfied: tcmlib==1.* in /usr/local/lib/python3.11/dist-packages (from tbb==2022.*->mkl->numpy>=1.17->sacrebleu) (1.2.0)\nRequirement already satisfied: intel-cmplr-lib-rt in /usr/local/lib/python3.11/dist-packages (from mkl_umath->numpy>=1.17->sacrebleu) (2024.2.0)\nRequirement already satisfied: intel-cmplr-lib-ur==2024.2.0 in /usr/local/lib/python3.11/dist-packages (from intel-openmp<2026,>=2024->mkl->numpy>=1.17->sacrebleu) (2024.2.0)\nDownloading sacrebleu-2.5.1-py3-none-any.whl (104 kB)\n\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m104.1/104.1 kB\u001b[0m \u001b[31m4.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hDownloading portalocker-3.1.1-py3-none-any.whl (19 kB)\nInstalling collected packages: portalocker, sacrebleu\nSuccessfully installed portalocker-3.1.1 sacrebleu-2.5.1\n","output_type":"stream"}],"execution_count":8},{"cell_type":"code","source":"import evaluate\n\nmetric = evaluate.load(\"sacrebleu\")\n\ndef compute_metrics(eval_preds):\n    preds, labels = eval_preds\n    decoded_preds = tokenizer.batch_decode(preds, skip_special_tokens=True)\n    decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True)\n\n    # Format references for sacreBLEU\n    decoded_labels = [[label] for label in decoded_labels]\n    result = metric.compute(predictions=decoded_preds, references=decoded_labels)\n    return {\"bleu\": result[\"score\"]}\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:03:40.736427Z","iopub.execute_input":"2025-05-12T07:03:40.736648Z","iopub.status.idle":"2025-05-12T07:03:41.733076Z","shell.execute_reply.started":"2025-05-12T07:03:40.736628Z","shell.execute_reply":"2025-05-12T07:03:41.732567Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"Downloading builder script:   0%|          | 0.00/8.15k [00:00<?, ?B/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"1f545853352242479dabe60645af14b5"}},"metadata":{}}],"execution_count":9},{"cell_type":"code","source":"trainer = Seq2SeqTrainer(\n    model=model,\n    args=training_args,\n    train_dataset=tokenized_dataset,\n    eval_dataset=tokenized_dataset,  # Optionally split later\n    tokenizer=tokenizer,\n    compute_metrics=compute_metrics,\n)\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:03:41.733761Z","iopub.execute_input":"2025-05-12T07:03:41.734552Z","iopub.status.idle":"2025-05-12T07:03:42.596712Z","shell.execute_reply.started":"2025-05-12T07:03:41.734533Z","shell.execute_reply":"2025-05-12T07:03:42.596146Z"}},"outputs":[{"name":"stderr","text":"/tmp/ipykernel_31/2624988232.py:1: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Seq2SeqTrainer.__init__`. Use `processing_class` instead.\n  trainer = Seq2SeqTrainer(\n","output_type":"stream"}],"execution_count":10},{"cell_type":"code","source":"trainer.train()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:03:42.597345Z","iopub.execute_input":"2025-05-12T07:03:42.597540Z","iopub.status.idle":"2025-05-12T07:10:25.134091Z","shell.execute_reply.started":"2025-05-12T07:03:42.597525Z","shell.execute_reply":"2025-05-12T07:10:25.133505Z"}},"outputs":[{"name":"stderr","text":"Passing a tuple of `past_key_values` is deprecated and will be removed in Transformers v4.48.0. You should pass an instance of `EncoderDecoderCache` instead, e.g. `past_key_values=EncoderDecoderCache.from_legacy_cache(past_key_values)`.\nPassing a tuple of `past_key_values` is deprecated and will be removed in Transformers v4.48.0. You should pass an instance of `EncoderDecoderCache` instead, e.g. `past_key_values=EncoderDecoderCache.from_legacy_cache(past_key_values)`.\n/usr/local/lib/python3.11/dist-packages/torch/nn/parallel/_functions.py:71: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n  warnings.warn(\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"<IPython.core.display.HTML object>","text/html":"\n    <div>\n      \n      <progress value='235' max='235' style='width:300px; height:20px; vertical-align: middle;'></progress>\n      [235/235 06:38, Epoch 5/5]\n    </div>\n    <table border=\"1\" class=\"dataframe\">\n  <thead>\n <tr style=\"text-align: left;\">\n      <th>Epoch</th>\n      <th>Training Loss</th>\n      <th>Validation Loss</th>\n      <th>Bleu</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <td>1</td>\n      <td>No log</td>\n      <td>0.063666</td>\n      <td>55.629836</td>\n    </tr>\n    <tr>\n      <td>2</td>\n      <td>0.799900</td>\n      <td>0.037102</td>\n      <td>61.046808</td>\n    </tr>\n    <tr>\n      <td>3</td>\n      <td>0.069800</td>\n      <td>0.024219</td>\n      <td>64.457362</td>\n    </tr>\n    <tr>\n      <td>4</td>\n      <td>0.048500</td>\n      <td>0.017581</td>\n      <td>66.436488</td>\n    </tr>\n    <tr>\n      <td>5</td>\n      <td>0.035700</td>\n      <td>0.015560</td>\n      <td>66.776644</td>\n    </tr>\n  </tbody>\n</table><p>"},"metadata":{}},{"name":"stderr","text":"/usr/local/lib/python3.11/dist-packages/torch/nn/parallel/_functions.py:71: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n  warnings.warn(\n/usr/local/lib/python3.11/dist-packages/torch/nn/parallel/_functions.py:71: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n  warnings.warn(\n/usr/local/lib/python3.11/dist-packages/torch/nn/parallel/_functions.py:71: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n  warnings.warn(\n/usr/local/lib/python3.11/dist-packages/torch/nn/parallel/_functions.py:71: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.\n  warnings.warn(\nThere were missing keys in the checkpoint model loaded: ['encoder.embed_tokens.weight', 'decoder.embed_tokens.weight', 'lm_head.weight'].\n","output_type":"stream"},{"execution_count":11,"output_type":"execute_result","data":{"text/plain":"TrainOutput(global_step=235, training_loss=0.207385449713849, metrics={'train_runtime': 402.1313, 'train_samples_per_second': 9.3, 'train_steps_per_second': 0.584, 'total_flos': 569375627673600.0, 'train_loss': 0.207385449713849, 'epoch': 5.0})"},"metadata":{}}],"execution_count":11},{"cell_type":"code","source":"model.save_pretrained('fine-tuned-model')\ntokenizer.save_pretrained('fine-tuned-model')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:14:04.305343Z","iopub.execute_input":"2025-05-12T07:14:04.305675Z","iopub.status.idle":"2025-05-12T07:14:06.289355Z","shell.execute_reply.started":"2025-05-12T07:14:04.305652Z","shell.execute_reply":"2025-05-12T07:14:06.288757Z"}},"outputs":[{"execution_count":12,"output_type":"execute_result","data":{"text/plain":"('fine-tuned-model/tokenizer_config.json',\n 'fine-tuned-model/special_tokens_map.json',\n 'fine-tuned-model/spiece.model',\n 'fine-tuned-model/added_tokens.json')"},"metadata":{}}],"execution_count":12},{"cell_type":"code","source":"model_path = \"fine-tuned-model\"\ntokenizer =  T5Tokenizer.from_pretrained(model_path)\nmodel = T5ForConditionalGeneration.from_pretrained(model_path).to(device)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:15:36.223783Z","iopub.execute_input":"2025-05-12T07:15:36.224070Z","iopub.status.idle":"2025-05-12T07:15:36.852201Z","shell.execute_reply.started":"2025-05-12T07:15:36.224050Z","shell.execute_reply":"2025-05-12T07:15:36.851424Z"}},"outputs":[],"execution_count":13},{"cell_type":"code","source":"def correct_grammar(sentence, max_length=128):\n    input_text = f\"fix: {sentence}\"\n    input_ids = tokenizer.encode(input_text, return_tensors=\"pt\", truncation=True).to(device)\n\n    with torch.no_grad():\n        output_ids = model.generate(\n            input_ids,\n            max_length=max_length,\n            num_beams=4,\n            early_stopping=True\n        )\n\n    corrected = tokenizer.decode(output_ids[0], skip_special_tokens=True)\n    return corrected\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:19:25.333413Z","iopub.execute_input":"2025-05-12T07:19:25.333721Z","iopub.status.idle":"2025-05-12T07:19:25.338410Z","shell.execute_reply.started":"2025-05-12T07:19:25.333699Z","shell.execute_reply":"2025-05-12T07:19:25.337639Z"}},"outputs":[],"execution_count":17},{"cell_type":"code","source":"samples = [\n    \"She go to school every day.\",\n    \"They is playing football in the park.\",\n    \"He don't like pizza.\",\n    \"They goes to park every sundays.\"\n]\n\nfor s in samples:\n    corrected = correct_grammar(s)\n    print(f\"Original: {s}\")\n    print(f\"Corrected: {corrected}\\n\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:21:06.801578Z","iopub.execute_input":"2025-05-12T07:21:06.802188Z","iopub.status.idle":"2025-05-12T07:21:07.603776Z","shell.execute_reply.started":"2025-05-12T07:21:06.802164Z","shell.execute_reply":"2025-05-12T07:21:07.603160Z"}},"outputs":[{"name":"stdout","text":"Original: She go to school every day.\nCorrected: She goes to school every day.\n\nOriginal: They is playing football in the park.\nCorrected: They are playing football in the park.\n\nOriginal: He don't like pizza.\nCorrected: He doesn't like pizza.\n\nOriginal: They goes to park every sundays.\nCorrected: They go to park every sundays.\n\n","output_type":"stream"}],"execution_count":22},{"cell_type":"code","source":"quantized_model = model.to(dtype=torch.float16, device=device)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:21:42.047111Z","iopub.execute_input":"2025-05-12T07:21:42.047713Z","iopub.status.idle":"2025-05-12T07:21:42.059751Z","shell.execute_reply.started":"2025-05-12T07:21:42.047690Z","shell.execute_reply":"2025-05-12T07:21:42.059142Z"}},"outputs":[],"execution_count":23},{"cell_type":"code","source":"quantized_model.save_pretrained('quantized-model')\ntokenizer.save_pretrained('quantized-model')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:21:59.132049Z","iopub.execute_input":"2025-05-12T07:21:59.132769Z","iopub.status.idle":"2025-05-12T07:22:00.115396Z","shell.execute_reply.started":"2025-05-12T07:21:59.132743Z","shell.execute_reply":"2025-05-12T07:22:00.114781Z"}},"outputs":[{"execution_count":24,"output_type":"execute_result","data":{"text/plain":"('quantized-model/tokenizer_config.json',\n 'quantized-model/special_tokens_map.json',\n 'quantized-model/spiece.model',\n 'quantized-model/added_tokens.json')"},"metadata":{}}],"execution_count":24},{"cell_type":"code","source":"model_name = '/kaggle/working/quantized-model'\nmodel = T5ForConditionalGeneration.from_pretrained(model_name).to(device)\ntokenizer = T5Tokenizer.from_pretrained(model_name)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:23:23.223377Z","iopub.execute_input":"2025-05-12T07:23:23.223670Z","iopub.status.idle":"2025-05-12T07:23:24.342694Z","shell.execute_reply.started":"2025-05-12T07:23:23.223651Z","shell.execute_reply":"2025-05-12T07:23:24.341763Z"}},"outputs":[],"execution_count":25},{"cell_type":"code","source":"def correct_grammar_fp16(sentence, max_length=128):\n    input_text = f\"fix: {sentence}\"\n    input_ids = tokenizer.encode(input_text, return_tensors=\"pt\", truncation=True).to(device)\n\n    with torch.no_grad():\n        output_ids = model.generate(\n            input_ids,\n            max_length=max_length,\n            num_beams=4,\n            early_stopping=True\n        )\n\n    corrected = tokenizer.decode(output_ids[0], skip_special_tokens=True)\n    return corrected","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:28:13.087696Z","iopub.execute_input":"2025-05-12T07:28:13.088388Z","iopub.status.idle":"2025-05-12T07:28:13.092734Z","shell.execute_reply.started":"2025-05-12T07:28:13.088364Z","shell.execute_reply":"2025-05-12T07:28:13.092028Z"}},"outputs":[],"execution_count":29},{"cell_type":"code","source":"samples = [\n    \"She go to school every day.\",\n    \"They is playing football in the park.\",\n    \"He don't like pizza.\",\n    \"They goes to park every sundays.\"\n]\n\nfor s in samples:\n    corrected = correct_grammar_fp16(s)\n    print(f\"Original: {s}\")\n    print(f\"Corrected: {corrected}\\n\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-12T07:28:17.807261Z","iopub.execute_input":"2025-05-12T07:28:17.808048Z","iopub.status.idle":"2025-05-12T07:28:18.553055Z","shell.execute_reply.started":"2025-05-12T07:28:17.808021Z","shell.execute_reply":"2025-05-12T07:28:18.552311Z"}},"outputs":[{"name":"stdout","text":"Original: She go to school every day.\nCorrected: She goes to school every day.\n\nOriginal: They is playing football in the park.\nCorrected: They are playing football in the park.\n\nOriginal: He don't like pizza.\nCorrected: He doesn't like pizza.\n\nOriginal: They goes to park every sundays.\nCorrected: They go to park every sundays.\n\n","output_type":"stream"}],"execution_count":30}]}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96457d6f2ed5ec1ebdaf3649e8d4437bbfbeb1bf0b605c65821067012d3efcff
+size 445837528

special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1,941 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}