Add `gpt-4-0125` and `gpt-3.5-turbo-1106` context sizes

[mikaelsouza]

There are a few new models released today from OpenAI

Links:

• https://openai.com/blog/new-embedding-models-and-api-updates
• https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo

So, I added gpt-4-0125-preview and gpt-3.5-turbo-1106 context sizes to the repo, so the library can report their context size correctly.

Can you check if these changes make sense? Thanks!

[zurawiki]

Small nit otherwise LGTM