[Remote Inference] Supported params are ignored

[kaisopos]

Description

Updates:

1. Validating that all params are supported, before the remote API call.
2. Adding 2 missing params (min_p, stop_token_ids) in _convert_conversation_to_api_input (base remote engine)
3. Open AI: Dropping logit_bias for "o1-preview" (this model was not working before)
4. Instead of always using the model params that were used when initializing the inference engine (self._model_params), this change allows users to update the model with a new inference config (inference_config.model) after the engine is instantiated. This allows users to use the same OpenAI engine for gpt-4, but later (without re-instantiating the engine) they can pass in a new config and run inference for OpenAI's o1-preview.

Related issues

Fixes OPE-1123

Before submitting

• This PR only changes documentation. (You can ignore the following checks in that case)
• Did you read the contributor guideline Pull Request guidelines?
• Did you link the issue(s) related to this PR in the section above?
• Did you add / update tests where needed?

Reviewers

At least one review from a member of oumi-ai/oumi-staff is required.

[kaisopos]

Note: min_p and stop_token_ids were newly added here

[kaisopos]

This function could be omitted, since logit_bias is empty by default & the super function has been updated to NOT include logit_bias in the API call if empty. This fn will only protect the user if they unintentionally set this. It is questionable though if it's a better experience to silently ignore this or just fail.