Find answers from the community

Updated 2 months ago

Llm

At a glance

The post asks which large language model (LLM) is the fastest and has the least response time when deployed as a chatbot. The comments suggest that community members could try using LLMs from the Grok or Cerebras platforms, as they claim to provide the fastest text generation. However, the comments also note that the performance depends on the model parameters and infrastructure, and that high-parameter models may be slower. One community member also asks if the Grok platform is open-source and how they can add a human feedback loop to train the model for better responses.

Which llm is fastest has least response time when deployed as a chatbot
@Logan M @WhiteFang_Jr
W
s
P
3 comments
You could try using llms from grok or cerebras platform. They claim to provide fastest text generation.
depends of the model param and the infra, expect slower token/second on high parameter model. Grok infra claim to be one of the fastest in the field
I don’t think it is opensource. Also can you suggest how can I add human feedback loop to train the model to give better response
@WhiteFang_Jr @saika @Logan M
Add a reply
Sign up and join the conversation on Discord