← Back to context

Comment by infinityio

4 years ago

I've had success with GPT-J (6B) [0] and GPT-NeoX (20B) [1], but they probably aren't quite the quality level you'll want to have

On the other hand, Facebook has recently released the weights for a few sizes of their OPT model [2]. I haven't tried it, but that might be worth looking into, because they claim that their model is comparable to Davinci

Note that for CPU inference you will be unable to use float16 datatypes, otherwise it might error out

[0] https://huggingface.co/EleutherAI/gpt-j-6B [1] https://huggingface.co/EleutherAI/gpt-neox-20b [2] https://huggingface.co/facebook/opt-66b

0 comments

infinityio

Reply