Repository navigation
Add the standard measuring protocol (#130 step 5) - #143
Merged
Merged
Conversation
results/README.md gains a Standard protocol section: the 512/256/1 comparison point, the optional grid, settings, repeats, how decode is timed, and the three details the issue left open (token counting, early stops, cache reuse). The Guidelines page links it and describes ranking within setups.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
No submission files to import. |
This was referenced Nov 18, 2026
This branch was successfully deployed
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Step 5 of #130.
results/README.md gets a Standard protocol section:
notes; decode is the streamed rate after the first token; at 4 requests, submit both a per-request file and a total file; record the revision, flags and model file.usage.completion_tokens), not by stream chunk; force the full length (ignore_eos/min_new_tokens) and rerun any run that stops early; keep repeats off the cache (cache_prompt: falseor a different first line per repeat).Guidelines page: the measuring advice links the protocol, and Ranking now describes setups instead of one best result per rig.
Docs and page copy only. No schema change or migration. Spread and the model file go in
notesuntil there are fields for them (step 4).