mirror of
https://github.com/RYDE-WORK/llama.cpp.git
synced 2026-01-22 07:38:21 +08:00
* llama : require first token to be BOS * scripts : add ppl-run-all.sh * perplexity : add BOS for each chunk * readme : update perplexity values after BOS fix * perplexity : add clarifying comments