together.Model.ready(model_name) #29
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 2 commits
September 15, 2023 11:56
clam004
requested review from
justin-together and
orangetin
and removed request for
orangetin
|
we decided to create a new API instead of do this via CLI |
orangetin
requested changes
Sep 15, 2023
|
|
||
| if response.status_code == 200: | ||
| response_json = response.json() | ||
| for model_dict in response_json: |
There was a problem hiding this comment.
Are there multiple model_dicts in response_json? If so, then return isn't going to return all of them.
| if model_dict.get("name") == model: | ||
| depth_num_asks = model_dict["depth"]["num_asks"] | ||
| if depth_num_asks > 0: | ||
| return {"ready":f"model is ready for start, status code:{depth_num_asks}"} |
There was a problem hiding this comment.
Let's replace "model" with the model name?
| if model_dict.get("name") == model: | ||
| depth_num_asks = model_dict["depth"]["num_asks"] | ||
| if depth_num_asks > 0: | ||
| return {"ready":f"model is ready for start, status code:{depth_num_asks}"} |
There was a problem hiding this comment.
I think we should have two keys in this dict. "ready" which is a bool and "message" which contains this text. That way it's easier for the end user to put this in a loop without having to parse the string.
|
Sorry for the false PR, the issue was updated that we should do this from the API end and not from the python library CLI end. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This PR fixes https://github.com/togethercomputer/planning/issues/2254. It allows users to check if their newly finetuned model is finished deploying and ready for completeions using our inference API:
the status code is our
depth_num_asks