Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update README.md to clarify context of models #203

Merged
merged 2 commits into from
Jan 30, 2024
Merged

Update README.md to clarify context of models #203

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a869f6a
Update README.md
logankilpatrick Oct 6, 2023
ede70dc
.
hauntsaninja Jan 30, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
.
  • Loading branch information
@hauntsaninja
hauntsaninja committed Jan 30, 2024
commit ede70dcc697ee7ad5c3061a43a8843db5f45d162
7 changes: 5 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@ The tokeniser API is documented in `tiktoken/core.py`.
Example code using `tiktoken` can be found in the
[OpenAI Cookbook](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb).


## Performance

`tiktoken` is between 3-6x faster than a comparable open source tokeniser:
Expand All @@ -31,6 +32,7 @@ Example code using `tiktoken` can be found in the
Performance measured on 1GB of text using the GPT-2 tokeniser, using `GPT2TokenizerFast` from
`tokenizers==0.13.2`, `transformers==4.24.0` and `tiktoken==0.2.0`.


## Getting help

Please post questions in the [issue tracker](https://github.com/openai/tiktoken/issues).
Expand All @@ -40,7 +42,7 @@ If you work at OpenAI, make sure to check the internal documentation or feel fre

## What is BPE anyway?

Large language models don't see text like you and I, instead they see a sequence of numbers (known as tokens).
Language models don't see text like you and I, instead they see a sequence of numbers (known as tokens).
Byte pair encoding (BPE) is a way of converting text into tokens. It has a couple desirable
properties:
1) It's reversible and lossless, so you can convert tokens back into the original text
Expand All @@ -65,10 +67,12 @@ enc = SimpleBytePairEncoding.from_tiktoken("cl100k_base")
enc.encode("hello world aaaaaaaaaaaa")
```


## Extending tiktoken

You may wish to extend `tiktoken` to support new encodings. There are two ways to do this.


**Create your `Encoding` object exactly the way you want and simply pass it around.**

```python
Expand Down Expand Up @@ -124,4 +128,3 @@ setup(

Then simply `pip install ./my_tiktoken_extension` and you should be able to use your
custom encodings! Make sure **not** to use an editable install.

Loading