Revision History
Code Llama · 13 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected the MultiPL-E table (all values wrong), StarCoder Base MBPP score (49.0%, not 43.6%), the 34B attention-head count, 70B long-context and infilling claims, a false 'first open-weight model to match GPT-4' claim, an invented rationale for the 34B lacking infilling, and an overstated Llama 2 license restriction (plus 19 minor fixes)
Version 13 · Nov 2, 2026, 05:24 PM
- Improve internal links (2026-10-13)
Version 11 · Oct 13, 2026, 10:09 AM
- Added 6 contextual internal links
Version 10 · Jul 23, 2026, 03:14 PM