docs: Models-used section + trim 0.5B/7B experiment detail - #3
Merged
Conversation
Adds a 'Models used' table (Qwen2.5-0.5B toy / 4-bit Mistral-7B / Qwen2.5-14B headline). Condenses the 0.5B + int4-7B write-ups (tables, the benchmark graph, memory-scaling table) into one short paragraph, and tightens engineering highlights. The 14B headline (table, plot, per-prompt speedups, demo GIF) is unchanged.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a Models used table and trims the earlier-target (0.5B / int4-7B) write-ups to a short paragraph (removing their tables, the benchmark graph, and the memory-scaling table). The 14B headline — results table, plot, per-prompt speedups, and the demo GIF — is unchanged.
This is the trim + models content that didn't make it onto
mainearlier (PR #2 merged only the hero-GIF commit).🤖 Generated with Claude Code