tiktoken_ruby 0.0.8-x86_64-darwin → 0.0.9-x86_64-darwin
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: dfffd99df0ef60ddd07eabefa385c8f4e56ed814063933118d7043c06811e7f5
|
4
|
+
data.tar.gz: 40f71bfc9ffab7a3694f6f7761ba22ea33eb781a9c8ed10e335dbef7b41443ab
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8013c6cd1f87ee18997962f56b2af713c207842224affaed762e5156c8c9ce37f6f01eef1fe07731cf763fe8c7cd820789968e4afb481be5b7876b73bf64c458
|
7
|
+
data.tar.gz: c8eff716ffefcfafb3fe3a456fe18709241d611ef66237aeb67c4187181e4d1b53b23cddf494127ad02b8f2d20b1ca512f97320135d2a005f76b279fdbdb17b4
|
data/Gemfile.lock
CHANGED
Binary file
|
Binary file
|
Binary file
|
data/lib/tiktoken_ruby.rb
CHANGED
@@ -64,13 +64,15 @@ module Tiktoken
|
|
64
64
|
:r50k_base,
|
65
65
|
:p50k_base,
|
66
66
|
:p50k_edit,
|
67
|
-
:cl100k_base
|
67
|
+
:cl100k_base,
|
68
|
+
:o200k_base
|
68
69
|
]
|
69
70
|
|
70
71
|
# taken from the python library here https://github.com/openai/tiktoken/blob/main/tiktoken/model.py
|
71
72
|
# that is also MIT licensed but by OpenAI
|
72
73
|
MODEL_TO_ENCODING_NAME = {
|
73
74
|
# chat
|
75
|
+
"gpt-4o": "o200k_base",
|
74
76
|
"gpt-4": "cl100k_base",
|
75
77
|
"gpt-3.5-turbo": "cl100k_base",
|
76
78
|
"gpt-35-turbo": "cl100k_base", # Azure deployment name
|
@@ -120,6 +122,7 @@ module Tiktoken
|
|
120
122
|
|
121
123
|
MODEL_PREFIX_TO_ENCODING = {
|
122
124
|
# chat
|
125
|
+
"gpt-4o-": "o200k_base", # e.g., gpt-4o-2024-05-13, etc.
|
123
126
|
"gpt-4-": "cl100k_base", # e.g., gpt-4-0314, etc., plus gpt-4-32k
|
124
127
|
"gpt-3.5-turbo-": "cl100k_base", # e.g, gpt-3.5-turbo-0301, -0401, etc.
|
125
128
|
"gpt-35-turbo-": "cl100k_base", # Azure deployment name
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: tiktoken_ruby
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.9
|
5
5
|
platform: x86_64-darwin
|
6
6
|
authors:
|
7
7
|
- IAPark
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2024-
|
11
|
+
date: 2024-05-16 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: An unofficial Ruby wrapper for Tiktoken, a BPE tokenizer written by and
|
14
14
|
used by OpenAI. It can be used to count the number of tokens in text before sending
|