sampling : support for llguidance grammars (#10224)
* initial porting of previous LLG patch * update for new APIs * build: integrate llguidance as an external project * use '%llguidance' as marker to enable llg lark syntax * add some docs * clarify docs * code style fixes * remove llguidance.h from .gitignore * fix tests when llg is enabled * pass vocab not model to llama_sampler_init_llg() * copy test-grammar-integration.cpp to test-llguidance.cpp * clang fmt * fix ref-count bug * build and run test * gbnf -> lark syntax * conditionally include llguidance test based on LLAMA_LLGUIDANCE flag * rename llguidance test file to test-grammar-llguidance.cpp * add gh action for llg test * align tests with LLG grammar syntax and JSON Schema spec * llama_tokenizer() in fact requires valid utf8 * update llg * format file * add $LLGUIDANCE_LOG_LEVEL support * fix whitespace * fix warning * include <cmath> for INFINITY * add final newline * fail llama_sampler_init_llg() at runtime * Link gbnf_to_lark.py script; fix links; refer to llg docs for lexemes * simplify #includes * improve doc string for LLAMA_LLGUIDANCE * typo in merge * bump llguidance to 0.6.12
This commit is contained in:
parent
0cec062a63
commit
ff227703d6
13 changed files with 1555 additions and 9 deletions
|
@ -991,7 +991,14 @@ public:
|
|||
}
|
||||
};
|
||||
|
||||
std::string json_schema_to_grammar(const json & schema) {
|
||||
std::string json_schema_to_grammar(const json & schema, bool force_gbnf) {
|
||||
#ifdef LLAMA_USE_LLGUIDANCE
|
||||
if (!force_gbnf) {
|
||||
return "%llguidance {}\nstart: %json " + schema.dump();
|
||||
}
|
||||
#else
|
||||
(void)force_gbnf;
|
||||
#endif // LLAMA_USE_LLGUIDANCE
|
||||
return build_grammar([&](const common_grammar_builder & callbacks) {
|
||||
auto copy = schema;
|
||||
callbacks.resolve_refs(copy);
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue