OpenGVLab
Is there no direct alternative to VLM models like we have InternLMForCausalLM? #8
Unanswered
SidInamdar
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
I am new to trying VLMs. I have a specific interest in trying to work on InternVL2_5 models. But matching model from huggingface and benchmarking on VLMEvalKit workflows is a hassle, claude tokens maxed out debugging. One thing I found was InternLM2ForCausalLM has no place for vision encoder. Hence, model.chat() is the default way. Is there a way we can simplify that? Just asking and forgive my ignorance.
All reactions