| license: apache-2.0 | |
| Upstage `solar-pro` tokenizer | |
| - Vocab size: 64,000 | |
| - Langauge support: English, Korean and more | |
| Please use this tokenizer for tokenizing inputs for the Upstage [solar-pro](https://developers.upstage.ai/docs/apis/chat) model. | |
| You can load it with the tokenizer library like this: | |
| ```python | |
| from tokenizers import Tokenizer | |
| tokenizer = Tokenizer.from_pretrained("upstage/solar-pro-tokenizer") | |
| text = "Hi, how are you?" | |
| enc = tokenizer.encode(text) | |
| print("Encoded input:") | |
| print(enc) | |
| inv_vocab = {v: k for k, v in tokenizer.get_vocab().items()} | |
| tokens = [inv_vocab[token_id] for token_id in enc.ids] | |
| print("Tokens:") | |
| print(tokens) | |
| number_of_tokens = len(enc.ids) | |
| print("Number of tokens:", number_of_tokens) | |
| ``` |