Archives/openai-cookbook
2
0
Fork 0
mirror of https://github.com/openai/openai-cookbook synced 2024-11-19 15:25:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #294 from dmitry-brazhenko/main

Browse Source 
Added sharptoken as example
This commit is contained in:
Ted Sanders 2023-03-28 09:42:30 -07:00 committed by GitHub
commit 470eb33b47
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
examples/How_to_count_tokens_with_tiktoken.ipynb
View File

@ -1,7 +1,6 @@
{ {
"cells": [ "cells": [
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -35,8 +34,9 @@
"\n", "\n",
"## Tokenizer libraries by language\n", "## Tokenizer libraries by language\n",
"\n", "\n",
"For `cl100k_base` and `p50k_base` encodings, `tiktoken` is the only tokenizer available as of March 2023.\n", "For `cl100k_base` and `p50k_base` encodings:\n",
"- Python: [tiktoken](https://github.com/openai/tiktoken/blob/main/README.md)\n", "- Python: [tiktoken](https://github.com/openai/tiktoken/blob/main/README.md)\n",
"- .NET / C#: [SharpToken](https://github.com/dmitry-brazhenko/SharpToken)\n",
"\n", "\n",
"For `r50k_base` (`gpt2`) encodings, tokenizers are available in many languages.\n", "For `r50k_base` (`gpt2`) encodings, tokenizers are available in many languages.\n",
"- Python: [tiktoken](https://github.com/openai/tiktoken/blob/main/README.md) (or alternatively [GPT2TokenizerFast](https://huggingface.co/docs/transformers/model_doc/gpt2#transformers.GPT2TokenizerFast))\n", "- Python: [tiktoken](https://github.com/openai/tiktoken/blob/main/README.md) (or alternatively [GPT2TokenizerFast](https://huggingface.co/docs/transformers/model_doc/gpt2#transformers.GPT2TokenizerFast))\n",
@ -54,7 +54,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -88,7 +87,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -105,7 +103,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -126,7 +123,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -143,7 +139,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -152,7 +147,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -180,7 +174,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -221,7 +214,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -229,7 +221,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -257,7 +248,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -265,7 +255,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -293,7 +282,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -301,7 +289,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -424,7 +411,6 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
@ -549,7 +535,7 @@
], ],
"metadata": { "metadata": {
"kernelspec": { "kernelspec": {
"display_name": "openai", "display_name": "Python 3",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -563,9 +549,8 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.9.9" "version": "3.7.3"
}, },
"orig_nbformat": 4,
"vscode": { "vscode": {
"interpreter": { "interpreter": {
"hash": "365536dcbde60510dc9073d6b991cd35db2d9bac356a11f5b64279a5e6708b97" "hash": "365536dcbde60510dc9073d6b991cd35db2d9bac356a11f5b64279a5e6708b97"