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

Updates the token count doc with GPT-4o and removes the deprecated version GPT-4-0314. #1212

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
+44 −38
Open

Updates the token count doc with GPT-4o and removes the deprecated version GPT-4-0314. #1212

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d7a5352
feat: update of token count documentation with gpt-4o and removing de…
DaviReisVieira May 14, 2024
f21783e
feat: Add Davi Reis as an author for the registry.yaml file
DaviReisVieira May 14, 2024
4ff6ffd
Merge branch 'main' into main
DaviReisVieira May 26, 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
5 changes: 5 additions & 0 deletions authors.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,3 +97,8 @@ justonf:
name: "Juston Forte"
website: "https://www.linkedin.com/in/justonforte/"
avatar: "https://avatars.githubusercontent.com/u/96567547?s=400&u=08b9757200906ab12e3989b561cff6c4b95a12cb&v=4"

davi-reis-vieira:
name: "Davi Reis"
website: "https://www.linkedin.com/in/davireisvieira/"
avatar: "https://avatars.githubusercontent.com/u/36394034?v=4"
74 changes: 37 additions & 37 deletions examples/How_to_count_tokens_with_tiktoken.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
"\n",
"| Encoding name | OpenAI models |\n",
"|-------------------------|-----------------------------------------------------|\n",
"| `cl100k_base` | `gpt-4`, `gpt-3.5-turbo`, `text-embedding-ada-002`, `text-embedding-3-small`, `text-embedding-3-large` |\n",
"| `cl100k_base` | `gpt-4o`, `gpt-4`, `gpt-3.5-turbo`, `text-embedding-ada-002`, `text-embedding-3-small`, `text-embedding-3-large` |\n",
"| `p50k_base` | Codex models, `text-davinci-002`, `text-davinci-003`|\n",
"| `r50k_base` (or `gpt2`) | GPT-3 models like `davinci` |\n",
"\n",
Expand Down Expand Up @@ -110,11 +110,11 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"encoding = tiktoken.get_encoding(\"cl100k_base\")\n"
"encoding = tiktoken.get_encoding(\"cl100k_base\")"
]
},
{
Expand All @@ -127,7 +127,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -153,7 +153,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 4,
"metadata": {},
"outputs": [
{
Expand All @@ -162,13 +162,13 @@
"[83, 1609, 5963, 374, 2294, 0]"
]
},
"execution_count": 5,
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"encoding.encode(\"tiktoken is great!\")\n"
"encoding.encode(\"tiktoken is great!\")"
]
},
{
Expand All @@ -181,20 +181,20 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"def num_tokens_from_string(string: str, encoding_name: str) -> int:\n",
" \"\"\"Returns the number of tokens in a text string.\"\"\"\n",
" encoding = tiktoken.get_encoding(encoding_name)\n",
" num_tokens = len(encoding.encode(string))\n",
" return num_tokens\n"
" return num_tokens"
]
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 6,
"metadata": {},
"outputs": [
{
Expand All @@ -203,13 +203,13 @@
"6"
]
},
"execution_count": 7,
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"num_tokens_from_string(\"tiktoken is great!\", \"cl100k_base\")\n"
"num_tokens_from_string(\"tiktoken is great!\", \"cl100k_base\")"
]
},
{
Expand All @@ -230,7 +230,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 7,
"metadata": {},
"outputs": [
{
Expand All @@ -239,13 +239,13 @@
"'tiktoken is great!'"
]
},
"execution_count": 8,
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"encoding.decode([83, 1609, 5963, 374, 2294, 0])\n"
"encoding.decode([83, 1609, 5963, 374, 2294, 0])"
]
},
{
Expand All @@ -266,7 +266,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 8,
"metadata": {},
"outputs": [
{
Expand All @@ -275,13 +275,13 @@
"[b't', b'ik', b'token', b' is', b' great', b'!']"
]
},
"execution_count": 9,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"[encoding.decode_single_token_bytes(token) for token in [83, 1609, 5963, 374, 2294, 0]]\n"
"[encoding.decode_single_token_bytes(token) for token in [83, 1609, 5963, 374, 2294, 0]]"
]
},
{
Expand All @@ -304,7 +304,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -321,13 +321,12 @@
" print()\n",
" print(f\"{encoding_name}: {num_tokens} tokens\")\n",
" print(f\"token integers: {token_integers}\")\n",
" print(f\"token bytes: {token_bytes}\")\n",
" "
" print(f\"token bytes: {token_bytes}\")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 10,
"metadata": {},
"outputs": [
{
Expand All @@ -352,12 +351,12 @@
}
],
"source": [
"compare_encodings(\"antidisestablishmentarianism\")\n"
"compare_encodings(\"antidisestablishmentarianism\")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 11,
"metadata": {},
"outputs": [
{
Expand All @@ -382,12 +381,12 @@
}
],
"source": [
"compare_encodings(\"2 + 2 = 4\")\n"
"compare_encodings(\"2 + 2 = 4\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 12,
"metadata": {},
"outputs": [
{
Expand All @@ -412,7 +411,7 @@
}
],
"source": [
"compare_encodings(\"お誕生日おめでとう\")\n"
"compare_encodings(\"お誕生日おめでとう\")"
]
},
{
Expand All @@ -422,9 +421,9 @@
"source": [
"## 6. Counting tokens for chat completions API calls\n",
"\n",
"ChatGPT models like `gpt-3.5-turbo` and `gpt-4` use tokens in the same way as older completions models, but because of their message-based formatting, it's more difficult to count how many tokens will be used by a conversation.\n",
"ChatGPT models like `gpt-3.5-turbo`, `gpt-4` and `gpt-4o` use tokens in the same way as older completions models, but because of their message-based formatting, it's more difficult to count how many tokens will be used by a conversation.\n",
"\n",
"Below is an example function for counting tokens for messages passed to `gpt-3.5-turbo` or `gpt-4`.\n",
"Below is an example function for counting tokens for messages passed to `gpt-3.5-turbo`, `gpt-4` or `gpt-4o`.\n",
"\n",
"Note that the exact way that tokens are counted from messages may change from model to model. Consider the counts from the function below an estimate, not a timeless guarantee.\n",
"\n",
Expand All @@ -433,7 +432,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -451,6 +450,7 @@
" \"gpt-4-32k-0314\",\n",
" \"gpt-4-0613\",\n",
" \"gpt-4-32k-0613\",\n",
" \"gpt-4o\",\n",
" }:\n",
" tokens_per_message = 3\n",
" tokens_per_name = 1\n",
Expand All @@ -475,12 +475,12 @@
" if key == \"name\":\n",
" num_tokens += tokens_per_name\n",
" num_tokens += 3 # every reply is primed with <|start|>assistant<|message|>\n",
" return num_tokens\n"
" return num_tokens"
]
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 14,
"metadata": {},
"outputs": [
{
Expand All @@ -500,10 +500,6 @@
"129 prompt tokens counted by num_tokens_from_messages().\n",
"129 prompt tokens counted by the OpenAI API.\n",
"\n",
"gpt-4-0314\n",
"129 prompt tokens counted by num_tokens_from_messages().\n",
"129 prompt tokens counted by the OpenAI API.\n",
"\n",
"gpt-4-0613\n",
"129 prompt tokens counted by num_tokens_from_messages().\n",
"129 prompt tokens counted by the OpenAI API.\n",
Expand All @@ -512,6 +508,10 @@
"Warning: gpt-4 may update over time. Returning num tokens assuming gpt-4-0613.\n",
"129 prompt tokens counted by num_tokens_from_messages().\n",
"129 prompt tokens counted by the OpenAI API.\n",
"\n",
"gpt-4o\n",
"124 prompt tokens counted by num_tokens_from_messages().\n",
"124 prompt tokens counted by the OpenAI API.\n",
"\n"
]
}
Expand Down Expand Up @@ -559,9 +559,9 @@
" \"gpt-3.5-turbo-0301\",\n",
" \"gpt-3.5-turbo-0613\",\n",
" \"gpt-3.5-turbo\",\n",
" \"gpt-4-0314\",\n",
" \"gpt-4-0613\",\n",
" \"gpt-4\",\n",
" \"gpt-4o\",\n",
" ]:\n",
" print(model)\n",
" # example token count from the function defined above\n",
Expand Down
3 changes: 2 additions & 1 deletion registry.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,9 +167,10 @@

- title: How to count tokens with Tiktoken
path: examples/How_to_count_tokens_with_tiktoken.ipynb
date: 2022-12-16
date: 2024-05-14
authors:
- ted-at-openai
- davi-reis-vieira
tags:
- tiktoken
- completions
Expand Down