From 84e09a7d8bc4ab6d658b5cd81295ac0add60be78 Mon Sep 17 00:00:00 2001
From: Evan Jones <evan.q.jones@gmail.com>
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 <henv@hot.ee>

* 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 <henv@hot.ee>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---
 examples/grammar-parser.h | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)
 create mode 100644 examples/grammar-parser.h

(limited to 'examples/grammar-parser.h')

diff --git a/examples/grammar-parser.h b/examples/grammar-parser.h
new file mode 100644
index 00000000..9037d727
--- /dev/null
+++ b/examples/grammar-parser.h
@@ -0,0 +1,29 @@
+// Implements a parser for an extended Backus-Naur form (BNF), producing the
+// binary context-free grammar format specified by llama.h. Supports character
+// ranges, grouping, and repetition operators. As an example, a grammar for
+// arithmetic might look like:
+//
+// root  ::= expr
+// expr  ::= term ([-+*/] term)*
+// term  ::= num | "(" space expr ")" space
+// num   ::= [0-9]+ space
+// space ::= [ \t\n]*
+
+#pragma once
+#include "llama.h"
+#include <vector>
+#include <map>
+#include <cstdint>
+#include <string>
+
+namespace grammar_parser {
+    struct parse_state {
+        std::map<std::string, uint32_t>                 symbol_ids;
+        std::vector<std::vector<llama_grammar_element>> rules;
+
+        std::vector<const llama_grammar_element *> c_rules();
+    };
+
+    parse_state parse(const char * src);
+    void print_grammar(FILE * file, const parse_state & state);
+}
-- 
cgit v1.2.3