Closed appleboy closed 8 months ago
Attention: 31 lines
in your changes are missing coverage. Please review.
Comparison is base (
ca7dcdd
) 22.93% compared to head (eb5b654
) 21.96%.
:exclamation: Your organization needs to install the Codecov GitHub app to enable full functionality.
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
openai.WithTopP(float32(viper.GetFloat64("openai.top_p")))
tocommit.go
openai.WithFrequencyPenalty(float32(viper.GetFloat64("openai.frequency_penalty")))
tocommit.go
openai.WithPresencePenalty(float32(viper.GetFloat64("openai.presence_penalty")))
tocommit.go
openai.top_p
toavailableKeys
inconfig.go
openai.frequency_penalty
toavailableKeys
inconfig.go
openai.presence_penalty
toavailableKeys
inconfig.go
configCmd.PersistentFlags().Float32P("top_p", "", 1.0, "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.")
toconfig.go
configCmd.PersistentFlags().Float32P("frequency_penalty", "", 0.0, "Number between 0.0 and 1.0 that penalizes new tokens based on their existing frequency in the text so far. Decreases the model's likelihood to repeat the same line verbatim.")
toconfig.go
ref #120