Text Generation
Transformers
Safetensors
English
Chinese
llama
conversational
text-generation-inference
Inference Endpoints

FIM task

#2
by danielus - opened

Hi! I read the paper and found nothing about fill in the middle, but < fim_prefix > suffix and middle tokens are present.
is it possible to use this model for autocomplete code?

inftech.ai org

Hi! Unfortunately OpenCoder doesn't support the FIM task. Our model added this token due to certain historical considerations.

I found this dataset
https://huggingface.co./datasets/Etherll/code-fim-v2
Can we finetuned with this?

inftech.ai org

@djuna It's recommend to learn FIM through pretrain stage instead of alignment stage :-)

I see...

Simingh changed discussion status to closed

Sign up or log in to comment