Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image models in Holistic Evaluation of Text-to-Image Models (HEIM) (https://arxiv.org/abs/2311.04287).
When I tried to run the together/llama-3-8b-chat and together/llama-3-70b-chat models with the default setup in src/helm/config/model_deployments.yaml, both models have client_spec set to "helm.clients.together_client.TogetherClient". However, this leads to many strange behaviors at generation time, such as repetition of instructions or outputting "..." as the answer.
This behavior stopped after I updated src/helm/config/model_deployments.yaml to reset the client_spec to "helm.clients.together_client.TogetherChatClient". I wonder whether this is a better client to handle these chat models and perhaps should be the default?
When I tried to run the
together/llama-3-8b-chat
andtogether/llama-3-70b-chat
models with the default setup insrc/helm/config/model_deployments.yaml
, both models haveclient_spec
set to"helm.clients.together_client.TogetherClient"
. However, this leads to many strange behaviors at generation time, such as repetition of instructions or outputting "..." as the answer.This behavior stopped after I updated
src/helm/config/model_deployments.yaml
to reset theclient_spec
to"helm.clients.together_client.TogetherChatClient"
. I wonder whether this is a better client to handle these chat models and perhaps should be the default?Thank!