File size: 5,465 Bytes
ccf8da6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import os \n",
"from transformers import AutoConfig, AutoTokenizer, AutoModelForSequenceClassification, DataCollatorWithPadding"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"model_name_or_path = \"/datadrive/namlh31/codebridge/Codebert-docstring-inconsistency\"\n",
"config = AutoConfig.from_pretrained(\n",
" model_name_or_path,\n",
")\n",
"tokenizer = AutoTokenizer.from_pretrained(\n",
" model_name_or_path\n",
")\n",
"model = AutoModelForSequenceClassification.from_pretrained(\n",
"model_name_or_path,\n",
"config=config,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"examples = {'code': \"function(str){\\r\\n var ret = new Array(str.length), len = str.length;\\r\\n while(len--) ret[len] = str.charCodeAt(len);\\r\\n return Uint8Array.from(ret);\\r\\n}\",\n",
" 'docstring': 'we do not need Buffer pollyfill for now'}"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"texts = (\n",
" (examples['docstring'], examples['code'])\n",
" )\n",
"result = tokenizer(*texts, padding=\"max_length\", max_length=512, truncation=True, return_tensors= 'pt')"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"512\n"
]
}
],
"source": [
"tokenizer.decode(result['input_ids'])\n",
"print(len(result['input_ids']))"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"input = \"\"\"we do not need Buffer pollyfill for now</s></s>function(str){\\r\\n var ret = new Array(str.length), len = str.length;\\r\\n while(len--) ret[len] = str.charCodeAt(len);\\r\\n return Uint8Array.from(ret);\\r\\n}\"\"\"\n",
"rs_2 = tokenizer(input, padding=\"max_length\", max_length=512, truncation=True, return_tensors= 'pt')"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"SequenceClassifierOutput(loss=None, logits=tensor([[ 0.2598, -0.2636]], grad_fn=<AddmmBackward0>), hidden_states=None, attentions=None)"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model(**rs_2)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
"To disable this warning, you can either:\n",
"\t- Avoid using `tokenizers` before the fork if possible\n",
"\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
"huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
"To disable this warning, you can either:\n",
"\t- Avoid using `tokenizers` before the fork if possible\n",
"\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
"huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
"To disable this warning, you can either:\n",
"\t- Avoid using `tokenizers` before the fork if possible\n",
"\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
]
}
],
"source": [
"from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline\n",
"import torch\n",
"device = 0 if torch.cuda.is_available() else -1\n",
"pipeline = pipeline(\"text-classification\", model=model, tokenizer=tokenizer, device=device)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[{'label': 'Inconsistency', 'score': 0.5601343512535095}]\n"
]
}
],
"source": [
"inputs = \"\"\"we do not need Buffer pollyfill for now</s></s>function(str){\n",
" var ret = new Array(str.length), len = str.length;\n",
" while(len--) ret[len] = str.charCodeAt(len);\n",
" return Uint8Array.from(ret);\n",
"}\"\"\"\n",
"prediction = pipeline(inputs)\n",
"print(prediction)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "namlh31",
"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": "3.11.2"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|