Open tkfv opened 3 months ago
What behaviour would you expect to see when you run llm models
?
For instance:
...
OpenAI Chat: gpt-4-turbo (aliases: gpt-4-turbo-preview, 4-turbo, 4t)
OpenAI Chat: gpt-4o (aliases: 4o, gpt-4o-2024-05-13)
OpenAI Chat: gpt-4o-latest (aliases: 4o-latest, gpt-4o-2024-08-06)
OpenAI Chat: gpt-4o-mini (aliases: 4o-mini)
...
I'm unsure on the preferred date-based naming convention: e.g.
OpenAI Chat: gpt-4-1106-preview
OpenAI Chat: gpt-4-0125-preview
OpenAI Chat: gpt-4-turbo-2024-04-09
OpenAI Chat: gpt-4-turbo (aliases: gpt-4-turbo-preview, 4-turbo, 4t)
OpenAI Chat: gpt-4o-2024-05-13 (aliases: 4o, gpt-4o)
OpenAI Chat: gpt-4o-2024-08-06 (aliases: 4o-latest)
Also this new model too:
OpenAI Chat: chatgpt-4o-latest
In the meantime you could add the following to your extra-openai-models.yaml
- model_id: gpt-4o-2024-08-06
aliases: ["4o-latest"]
model_name: "gpt-4o-2024-08-06"
Instructions at openai-language-models
hi Simon, I read yesterday post on your blog, llm needs to support the new model. Thank you!