jyapayne/dify
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

azure openai add gpt-4-1106-preview、gpt-4-vision-preview models (#1751)

Browse source 
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
This commit is contained in:
Charlie.Wei 2023-12-14 09:55:30 +08:00 • committed by GitHub
commit b0d8d196e1
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 811 additions and 336 deletions
Download patch file Download diff file Expand all files Collapse all files

2
web/i18n/lang/common.en.ts
View file

@ -65,7 +65,7 @@ const translation = {
'How much to penalize new tokens based on their existing frequency in the text so far.\nDecreases the model\'s likelihood to repeat the same line verbatim.',
max_tokens: 'Max token',
max_tokensTip:
'Used to limit the maximum length of the reply, in tokens. \nLarger values may limit the space left for prompt words, chat logs, and Knowledge. \nIt is recommended to set it below two-thirds.',
'Used to limit the maximum length of the reply, in tokens. \nLarger values may limit the space left for prompt words, chat logs, and Knowledge. \nIt is recommended to set it below two-thirds\ngpt-4-1106-preview, gpt-4-vision-preview max token (input 128k output 4k)',
maxTokenSettingTip: 'Your max token setting is high, potentially limiting space for prompts, queries, and data. Consider setting it below 2/3.',
setToCurrentModelMaxTokenTip: 'Max token is updated to the 80% maximum token of the current model {{maxToken}}.',
stop_sequences: 'Stop sequences',