File size: 1,114 Bytes
bb39a0d 44c70f0 bb39a0d 44c70f0 |
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 |
---
tags:
- ci
---
## Dummy model used for unit testing and CI
```python
import json
import os
from transformers import RobertaConfig, RobertaForMaskedLM, TFRobertaForMaskedLM
DIRNAME = "./dummy-unknown"
config = RobertaConfig(10, 20, 1, 1, 40)
model = RobertaForMaskedLM(config)
model.save_pretrained(DIRNAME)
tf_model = TFRobertaForMaskedLM.from_pretrained(DIRNAME, from_pt=True)
tf_model.save_pretrained(DIRNAME)
# Tokenizer:
vocab = [
"l",
"o",
"w",
"e",
"r",
"s",
"t",
"i",
"d",
"n",
"\u0120",
"\u0120l",
"\u0120n",
"\u0120lo",
"\u0120low",
"er",
"\u0120lowest",
"\u0120newer",
"\u0120wider",
"<unk>",
]
vocab_tokens = dict(zip(vocab, range(len(vocab))))
merges = ["#version: 0.2", "\u0120 l", "\u0120l o", "\u0120lo w", "e r", ""]
vocab_file = os.path.join(DIRNAME, "vocab.json")
merges_file = os.path.join(DIRNAME, "merges.txt")
with open(vocab_file, "w", encoding="utf-8") as fp:
fp.write(json.dumps(vocab_tokens) + "\n")
with open(merges_file, "w", encoding="utf-8") as fp:
fp.write("\n".join(merges))
```
|