File size: 997 Bytes
9880769
 
 
 
 
 
 
 
 
 
70e3867
 
8cd8309
70e3867
 
 
 
8cd8309
9880769
c28f293
9880769
 
 
 
 
 
 
 
 
 
 
 
 
 
50d6cdc
9880769
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
import transformers
import os
import torch

MAX_LEN = 150 #256
TRAIN_BATCH_SIZE = 8
VALID_BATCH_SIZE = 4
EPOCHS = 5

# Folder to contain all the datasets
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="thak123/bert-emoji-latvian-twitter-classifier", filename="model.bin",local_dir="./")

# import requests
# URL = "https://huggingface.co/thak123/bert-emoji-latvian-twitter-classifier/resolve/main/model.bin"
# response = requests.get(URL)
# open("model.bin", "wb").write(response.content)

DATASET_LOCATION = "" # 
MODEL_PATH = "model.bin"

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# 7 EPOCH Version
BERT_PATH = "FFZG-cleopatra/bert-emoji-latvian-twitter"


# TODO check if lower casing is required
# BertTokenizer
TOKENIZER = transformers.BertTokenizer.from_pretrained(
    BERT_PATH,
    do_lower_case=True
)

####################################################################################################################################