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.

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

Feat Models [GPT-4] [GPT-3.5] [128K context] #3143

Merged
merged 3 commits into from
Nov 7, 2023

Conversation

H0llyW00dzZ
Copy link
Contributor

[+] feat(constant.ts): add new models to DEFAULT_MODELS array

Note :
The model has 128K context
read here https://openai.com/blog/new-models-and-developer-products-announced-at-devday

[+] feat(constant.ts): add new models to DEFAULT_MODELS array
[+] fix(constant.ts): fix typo in model name, change "ggpt-4-1106-preview" to "gpt-4-1106-preview"
[+] fix(constant.ts): update DEFAULT_SYSTEM_TEMPLATE to include knowledgeCutoff and time variables
[+] feat(chat.ts): add support for injecting system prompts based on model configuration
@H0llyW00dzZ
Copy link
Contributor Author

Refactor KnowledgeCutoff :

Knowledge Cutoff_ April 2023

Knowledge Cutoff_ April 2023 (1)

@Issues-translate-bot
Copy link

Bot detected the issue body's language is not English, translate it automatically.


Refactor KnowledgeCutoff :

Knowledge Cutoff_ April 2023

Knowledge Cutoff_ April 2023 (1)

vrichv added a commit to vrichv/ChatGPT-Next-Web-Pro-Max that referenced this pull request Nov 7, 2023
@Yidadaa Yidadaa merged commit 1096fe5 into ChatGPTNextWeb:main Nov 7, 2023
@H0llyW00dzZ H0llyW00dzZ deleted the newmodels branch November 7, 2023 03:13
spongeBor pushed a commit to spongeBor/ChatGPT-Next-Web that referenced this pull request Jan 18, 2024
gaogao1030 pushed a commit to gaogao1030/ChatGPT-Next-Web that referenced this pull request May 16, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants