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

Update chat completions models #21

Merged
merged 1 commit into from
Feb 13, 2024
Merged

Update chat completions models #21

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
61 changes: 36 additions & 25 deletions models/chat_completions.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,17 +22,14 @@ const (
// single request.
GPT3Dot5Turbo16K

// GPT4Dot5Turbo1106 is a snapshot of gpt-3.5-turbo from November 6th 2023.
//
// Release Notes:
// In addition to GPT-4 Turbo, we are also releasing a new version of GPT-3.5 Turbo that supports a 16K context window by default.
// The new 3.5 Turbo supports improved instruction following, JSON mode, and parallel function calling.
// For instance, our internal evals show a 38% improvement on format following tasks such as generating JSON, XML and YAML. Developers can access this new model by calling gpt-3.5-turbo-1106 in the API.
// GPT3Dot5Turbo1106 is a GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs,
// parallel function calling, and more. Returns a maximum of 4,096 output tokens.
GPT3Dot5Turbo1106

// GPT-4 models are currently in a limited beta and only accessible to those who have been granted access.
// Please join the waitlist to get access when capacity is available.
// https://openai.com/waitlist/gpt-4-api
// GPT3Dot5Turbo0125 is the latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a
// fix for a bug which caused a text encoding issue for non-English language function calls. Returns a maximum of
// 4,096 output tokens.
GPT3Dot5Turbo0125

// GPT4 is more capable than any GPT-3.5 model, able to do more complex tasks, and optimized for chat.
// Will be updated with our latest model iteration.
Expand Down Expand Up @@ -60,11 +57,19 @@ const (
//nolint:revive,stylecheck // This would be unreadable otherwise.
GPT4_32K_0613

// GPT-4 Turbo (gpt-4-1106-preview) is more capable and has knowledge of world events up to April 2023. It has a 128k context window so it can fit the equivalent of more than 300 pages of text in a single prompt.
// We also optimized its performance so we are able to offer GPT-4 Turbo at a 3x cheaper price for input tokens and a 2x cheaper price for output tokens compared to GPT-4.
//
// GPT-4 Turbo is available for all paying developers to try by passing gpt-4-1106-preview in the API and we plan to release the stable production-ready model in the coming weeks.
// GPT4Turbo1106Preview (GPT-4 Turbo) is more capable and has knowledge of world events up to April 2023. It has a
// 128k context window so it can fit the equivalent of more than 300 pages of text in a single prompt.
// It also optimized its performance so we are able to offer GPT-4 Turbo at a 3x cheaper price for input tokens and
// a 2x cheaper price for output tokens compared to GPT-4.
GPT4Turbo1106Preview

// GPT4Turbo0125Preview (GPT-4 Turbo) is the latest GPT-4 model intended to reduce cases of "laziness" where the model
// doesn’t complete a task. Returns a maximum of 4,096 output tokens.
GPT4Turbo0125Preview

// GPT4TurboPreview (GPT-4 Turbo) is the latest GPT-4. It currently points to gpt-4-0125-preview, however, may
// receive updates in the future.
GPT4TurboPreview
)

// String implements the fmt.Stringer interface.
Expand Down Expand Up @@ -96,26 +101,32 @@ var chatCompletionToString = map[ChatCompletion]string{
GPT3Dot5Turbo0613: "gpt-3.5-turbo-0613",
GPT3Dot5Turbo16K: "gpt-3.5-turbo-16k",
GPT3Dot5Turbo1106: "gpt-3.5-turbo-1106",
GPT3Dot5Turbo0125: "gpt-3.5-turbo-0125",
GPT4: "gpt-4",
GPT4_0613: "gpt-4-0613",
GPT4_0314: "gpt-4-0314",
GPT4_32K: "gpt-4-32k",
GPT4_32K_0314: "gpt-4-32k-0314",
GPT4_32K_0613: "gpt-4-32k-0613",
GPT4Turbo1106Preview: "gpt-4-1106-preview",
GPT4Turbo0125Preview: "gpt-4-0125-preview",
GPT4TurboPreview: "gpt-4-turbo-preview",
}

var stringToChatCompletion = map[string]ChatCompletion{
"gpt-3.5-turbo": GPT3Dot5Turbo,
"gpt-3.5-turbo-0301": GPT3Dot5Turbo0301,
"gpt-3.5-turbo-0613": GPT3Dot5Turbo0613,
"gpt-3.5-turbo-16k": GPT3Dot5Turbo16K,
"gpt-3.5-turbo-1106": GPT3Dot5Turbo1106,
"gpt-4": GPT4,
"gpt-4-0314": GPT4_0314,
"gpt-4-0613": GPT4_0613,
"gpt-4-32k": GPT4_32K,
"gpt-4-32k-0314": GPT4_32K_0314,
"gpt-4-32k-0613": GPT4_32K_0613,
"gpt-4-1106-preview": GPT4Turbo1106Preview,
"gpt-3.5-turbo": GPT3Dot5Turbo,
"gpt-3.5-turbo-0301": GPT3Dot5Turbo0301,
"gpt-3.5-turbo-0613": GPT3Dot5Turbo0613,
"gpt-3.5-turbo-16k": GPT3Dot5Turbo16K,
"gpt-3.5-turbo-1106": GPT3Dot5Turbo1106,
"gpt-3.5-turbo-0125": GPT3Dot5Turbo0125,
"gpt-4": GPT4,
"gpt-4-0314": GPT4_0314,
"gpt-4-0613": GPT4_0613,
"gpt-4-32k": GPT4_32K,
"gpt-4-32k-0314": GPT4_32K_0314,
"gpt-4-32k-0613": GPT4_32K_0613,
"gpt-4-1106-preview": GPT4Turbo1106Preview,
"gpt-4-0125-preview": GPT4Turbo0125Preview,
"gpt-4-turbo-preview": GPT4TurboPreview,
}
Loading