Encoder/Decoder and tokens counter for GPT3
Project description
An OpenAI GPT3 helper library for encoding/decoding strings and counting tokens.
Counting tokens gives the same output as OpenAI’s tokenizer
Tested with versions: 2.7.12, 2.7.18 and all 3.x.x versions
Installing
pip install gpt3_tokenizer
Examples
Encoding/decoding a string
import gpt3_tokenizer
a_string = "That's my beautiful and sweet string"
encoded = gpt3_tokenizer.encode(a_string) # outputs [2504, 338, 616, 4950, 290, 6029, 4731]
decoded = gpt3_tokenizer.decode(encoded) # outputs "That's my beautiful and sweet string"
Counting tokens
import gpt3_tokenizer
a_string = "That's my beautiful and sweet string"
tokens_count = gpt3_tokenizer.count_tokens(a_string) # outputs 7
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
gpt3_tokenizer-0.1.1.tar.gz
(560.7 kB
view hashes)
Built Distribution
Close
Hashes for gpt3_tokenizer-0.1.1-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 76eb85cf96ff983b1bbd158e7d69fec44ea51a932af73f6548fe25b122fab5dc |
|
MD5 | c6f01a429ab5f8c90e9f6cb1691031be |
|
BLAKE2b-256 | 1c8304830bef74a62a7c985d6e236331588b064b087facf78f176dd6a1b0652f |