88250
commented
1 year ago For the time being, only consider supporting gpt-4, gpt-4-32k and gpt-3.5-turbo. Other models may be used by fewer people and are more expensive, so we will not join them for the time being. Thanks for the suggestion.
In what scenarios do you need this feature?
Want to use GPT4 instead of GPT 3.5 Turbo
Describe the optimal solution
req := gogpt.ChatCompletionRequest{ Model: gogpt.GPT3Dot5Turbo, MaxTokens: maxTokens, Messages: reqMsgs, }
In above code, allow Model to be chosen from below list of Models
const ( GPT432K0314 = "gpt-4-32k-0314" GPT432K = "gpt-4-32k" GPT40314 = "gpt-4-0314" GPT4 = "gpt-4" GPT3Dot5Turbo0301 = "gpt-3.5-turbo-0301" GPT3Dot5Turbo = "gpt-3.5-turbo" GPT3TextDavinci003 = "text-davinci-003" GPT3TextDavinci002 = "text-davinci-002" GPT3TextCurie001 = "text-curie-001" GPT3TextBabbage001 = "text-babbage-001" GPT3TextAda001 = "text-ada-001" GPT3TextDavinci001 = "text-davinci-001" GPT3DavinciInstructBeta = "davinci-instruct-beta" GPT3Davinci = "davinci" GPT3CurieInstructBeta = "curie-instruct-beta" GPT3Curie = "curie" GPT3Ada = "ada" GPT3Babbage = "babbage" )
Describe the candidate solution
No response
Other information
No response