From 84e09a7d8bc4ab6d658b5cd81295ac0add60be78 Mon Sep 17 00:00:00 2001 From: Evan Jones Date: Sun, 23 Jul 2023 23:58:10 -0400 Subject: llama : add grammar-based sampling (#1773) * llama, main : constrain sampling to grammar * allow loading grammar from file * fix whitespace errors * handle & print parser errors * add comments to grammar syntax and allow newlines where unambiguous * add missing include * support alternates in root rule * fix bugs with empty token and EOS * adjust JSON grammar * remove swp file * rewrite ternary expressions Co-authored-by: Henri Vasserman * use struct for grammar elements and add Unicode support * add unicode escapes * add inverse char ranges * only sample full tokens (no peeking or truncation) * llama : minor style changes blindly applied in online editor - hopefully I didn't break something * update help text * add warning message if EOS is disabled --------- Co-authored-by: Henri Vasserman Co-authored-by: Georgi Gerganov --- examples/common.h | 1 + 1 file changed, 1 insertion(+) (limited to 'examples/common.h') diff --git a/examples/common.h b/examples/common.h index fb8f6d65..7086606b 100644 --- a/examples/common.h +++ b/examples/common.h @@ -63,6 +63,7 @@ struct gpt_params { std::string path_prompt_cache = ""; // path to file for saving/loading prompt eval state std::string input_prefix = ""; // string to prefix user inputs with std::string input_suffix = ""; // string to suffix user inputs with + std::string grammar = ""; // optional BNF-like grammar to constrain sampling std::vector antiprompt; // string upon seeing which more user input is prompted std::string lora_adapter = ""; // lora adapter path -- cgit v1.2.3