Adapt to use Hugging Face models (includes streaming) #3
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hi
I thought about how to implement the streaming functionality and saw that the only way was to re-write the generation functions in codellama, which seemed a bit messy. Simulaneously, Hugging Face released the models in their format, so I thought the easiest thing to do would be to use them.
Advantages:
load_in_4bit
flag)transformers
library, so you only have one instance of the server running (i.e., no need to mess withtorch.distributed
).text-inference-server
in the backend, which is much faster than the regular generation.Disadvantages:
I get responses similar to this:
and sometimes it spits out endless
\n
tokens instead of stopping when it should. When I run your code using the Meta checkpoints I get something likeI mean, the jokes are terrible, but at least it writes it in C as instructed.
Anyway, I thought I would create this Pull Request so you could play around with it. I'd be interested to know whether you think this is a good direction to go in.