Changed litellm prints to tqdm and added execution metrics #45
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
sidjha1
reviewed
Nov 27, 2024
|
can you test the examples and check that the output is as intended? map.py in examples still prints out the LiteLLM calls, and then it's followed by a tqdm output |
sidjha1
reviewed
Dec 6, 2024
sidjha1
reviewed
Dec 7, 2024
sidjha1
reviewed
Dec 7, 2024
sidjha1
approved these changes
Dec 7, 2024
lotus/models/lm.py
Outdated
| @@ -24,19 +29,23 @@ def __init__( | |||
| max_batch_size: int = 64, | |||
| tokenizer: Tokenizer | None = None, | |||
| max_cache_size: int = 1024, | |||
| safe_mode: bool = False, | |||
There was a problem hiding this comment.
We can remove safe_mode from LM because its not used here anymore.
lotus/sem_ops/sem_extract.py
Outdated
| @@ -47,6 +55,8 @@ def sem_extract( | |||
| lotus.logger.debug(f"raw_outputs: {lm_output.outputs}") | |||
| lotus.logger.debug(f"outputs: {postprocess_output.outputs}") | |||
|
|
|||
| model.print_total_usage() | |||
There was a problem hiding this comment.
Can we do model.print_total_usage everywhere only if we are in safe mode?
lotus/sem_ops/sem_topk.py
Outdated
| estimated_quicksort_calls = 2 * len(docs) * np.log(len(docs)) | ||
| estimated_total_calls = estimated_quickselect_calls + estimated_quicksort_calls | ||
| estimated_total_tokens = lotus.settings.lm.count_tokens(sample_prompt) * estimated_total_calls | ||
| print("Quicksort:") |
There was a problem hiding this comment.
Let's remove the Quicksort print, and similarly the Heap Sort print.
There was a problem hiding this comment.
@sidjha1 Naive sort as well?
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Outdated suggestions cannot be applied.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.
Replaced litellm prints with tqdm progress bar and added the execution metrics (cost and tokens)
Safe_mode implementation:
sem_extract - completed
sem_map - completed
sem_agg - completed
sem_topk - completed
sem_join - completed
sem_filter - completed