Function calling and Streaming support
Hi ,
I've been exploring the IBM Granite models and have a couple of questions that I'd appreciate if someone could help me with.
Function Calling: I haven't found any documentation or resources that indicate whether IBM Granite models support function calling, i.e., invoking a particular function or method of the model. Can anyone confirm if this feature is supported?
Streaming: Similarly, I'm also curious to know whether IBM Granite models support Streaming. any pointers or resources in this regard would be greatly appreciated.
I've searched through both the Git repo and Hugging Face documentation but haven't found clear information on these features. If anyone has any insights, it would be a great help.
Thanks.
Any help you could provide in above ?
Thanks.
@skumarai
function calling might work with the model but its not an actively trained feature AFAIK.
I think HuggingFace doesn't support streaming.
And streaming has nothing to do with the model but rather the HuggingFace ecosystem.
I suggest you take a look at vllm: https://github.com/vllm-project/vllm