mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-07-18 08:37:43 +00:00
* 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
perplexity
TODO