Find answers from the community

Updated 2 months ago

Anyone know what additional kwargs are

Anyone know what additional kwargs are allowed/expected for the OpenAILike llm? I was hoping to be able to pass parameters such as top p/k, repetition penalty, etc. but it doesn't seem those are supported. I assume since it's just a wrapper for OpenAI, options are limited. Worth creating a custom implementation or is it possible to modify the wrapper?
b
L
7 comments
How are you instantiating your LLM?
I use HuggingFaceLLM() from llama_index.llms.huggingface.
I'd see what I can throw in the generate_kwargs argument.
Or try passing them directly into HuggingFaceLLM()
I cannot find the documentation to exactly which params HuggingFaceLLM() accepts, but here's an example of its use:
Openailike will probably accept those under the additional_kwargs field
Add a reply
Sign up and join the conversation on Discord