Spaces:
Sleeping
Sleeping
File size: 2,259 Bytes
b83e315 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/timo/rep/TextClassifier/venv/lib/python3.12/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": [
"import os\n",
"os.chdir('..')\n",
"\n",
"import torch\n",
"from transformers import AutoTokenizer, AutoModel\n",
"from src import device"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"tokenizer = AutoTokenizer.from_pretrained(\"cointegrated/rubert-tiny\")\n",
"model = AutoModel.from_pretrained(\"cointegrated/rubert-tiny\")\n",
"\n",
"model = model.to(device)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"def embed_bert_cls(text, model, tokenizer):\n",
" t = tokenizer(text, padding=True, truncation=True, return_tensors='pt')\n",
" with torch.no_grad():\n",
" model_output = model(**{k: v.to(model.device) for k, v in t.items()})\n",
" embeddings = model_output.last_hidden_state[:, 0, :]\n",
" embeddings = torch.nn.functional.normalize(embeddings)\n",
" return embeddings[0].cpu().numpy()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(312,)\n"
]
}
],
"source": [
"print(embed_bert_cls('привет мир', model, tokenizer).shape)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"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": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|