Allow user to specify the tokenizer for compare #224
Merged
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Outdated suggestions cannot be applied.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.
A user mentioned that compare does not work with a non-default tokenizer: #174
This pull request enables passing in a tokenizer for compare to have more accurate token counts.
A couple of clean-up items:
Before the change
Command:
genai-perf compare -f artifacts/HuggingFaceH4_zephyr-7b-beta-openai-chat-concurrency1/profile_export.json artifacts/HuggingFaceH4_zephyr-7b-beta-openai-chat-concurrency2/profile_export.json
Graph:
After the change (with tokenizer specified):
Command:
genai-perf compare --tokenizer HuggingFaceH4/zephyr-7b-beta -f artifacts/HuggingFaceH4_zephyr-7b-beta-openai-chat-concurrency1/profile_export.json artifacts/HuggingFaceH4_zephyr-7b-beta-openai-chat-concurrency2/profile_export.json
Graph: