Text tokenizers.
Project description
totokenizers
A model-agnostic library to encode text into tokens and couting them using different tokenizers.
install
pip install totokenizers
usage
from totokenizers.factories import TotoModelInfo, Totokenizer
mdoel = "openai/gpt-3.5-turbo-0613"
desired_max_tokens = 250
tokenizer = Totokenizer.from_model(model)
model_info = TotoModelInfo.from_model(model)
thread_length = tokenizer.count_chatml_tokens(thread, functions)
if thread_length + desired_max_tokens > model_info.max_tokens:
raise YourException(thread_length, desired_max_tokens, model_info.max_tokens)
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
totokenizers-1.2.1.tar.gz
(754.0 kB
view details)
Built Distribution
totokenizers-1.2.1-py3-none-any.whl
(764.2 kB
view details)
File details
Details for the file totokenizers-1.2.1.tar.gz.
File metadata
- Download URL: totokenizers-1.2.1.tar.gz
- Upload date:
- Size: 754.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 59e61c9a9459e56276a601e49fa82d3d72c3b0c61ea9045b3077090226777086 |
|
| MD5 | 0faefd0132d2ad57888e0dc2b6812679 |
|
| BLAKE2b-256 | 11b64e186add05a6f2bf0ac1eb6ccba9e319b70596111ca3813b755ee0ea5968 |
Provenance
File details
Details for the file totokenizers-1.2.1-py3-none-any.whl.
File metadata
- Download URL: totokenizers-1.2.1-py3-none-any.whl
- Upload date:
- Size: 764.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 22a24eb4332bba3743629eec69565c1d032a7fda4f215b30f420a5e51db0eb2d |
|
| MD5 | df9f3961cb6792ed1adfa7529299f756 |
|
| BLAKE2b-256 | 52a55b2568f18e24e7e53a2d2c5d681fc8252135dbc02653894aeeb9fd8e54b0 |
