mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-07-28 13:20:27 -04:00
* 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