[DOC] [ml-commons] add new model config parameters

[ylwu-amzn]

What do you want to do?

• Request a change to existing documentation
• Add new documentation
• Report a technical problem with the documentation
• Other

Tell us about your request. Provide a summary of the request and all versions that are affected.

We add two new model parameters in 2.5 which not included in this doc https://opensearch.org/docs/latest/ml-commons-plugin/model-serving-framework/#the-model_config-object.

• "pooling_mode": type "string", If user trace model with Huggingface transformer, they may need to specify how to post-process model output by specifying "pooling_mode" and "normalize_result". Supported pooling method: mean, mean_sqrt_len, max, weightedmean, cls. For example, this huggingface model https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 uses mean pooling mode.
• "normalize_result": type "boolean". If user trace model with Huggingface transformer, they may need to specify how to post-process model output by specifying "pooling_mode" and "normalize_result". For example, this huggingface model https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 needs to normalize result, so need to set "normalize_result" as `true.

You can also read this doc for more details https://github.com/opensearch-project/ml-commons/blob/2.x/docs/model_serving_framework/text_embedding_model_examples.md,

What other resources are available? Provide links to related issues, POCs, steps for testing, etc.