vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.devops/llama-server.Dockerfile
#	.github/workflows/docker.yml
#	README.md
#	llama.cpp
#	tests/test-chat-template.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tests/test-llama-grammar.cpp
This commit is contained in:
Concedo 2024-06-26 18:59:10 +08:00
commit f3dfa96dbc
29 changed files with 2097 additions and 431 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama.h
View file

@ -67,6 +67,7 @@ extern "C" {
LLAMA_VOCAB_TYPE_SPM = 1, // LLaMA tokenizer based on byte-level BPE with byte fallback
LLAMA_VOCAB_TYPE_BPE = 2, // GPT-2 tokenizer based on byte-level BPE
LLAMA_VOCAB_TYPE_WPM = 3, // BERT tokenizer based on WordPiece
LLAMA_VOCAB_TYPE_UGM = 4, // T5 tokenizer based on Unigram
};
// pre-tokenization types
@ -859,6 +860,7 @@ extern "C" {
LLAMA_API llama_token llama_token_cls(const struct llama_model * model); // classification
LLAMA_API llama_token llama_token_sep(const struct llama_model * model); // sentence separator
LLAMA_API llama_token llama_token_nl (const struct llama_model * model); // next-line
LLAMA_API llama_token llama_token_pad(const struct llama_model * model); // padding
// Returns -1 if unknown, 1 for true or 0 for false.
LLAMA_API int32_t llama_add_bos_token(const struct llama_model * model);
@ -926,6 +928,12 @@ extern "C" {
// Grammar
//
/// Initialize a llama_grammar.
///
/// @param rules The rule elements of the grammar to initialize.
/// @param n_rules The number of rules.
/// @param start_rule_index The index of the root rule (the starting point of the grammar).
/// @return The initialized llama_grammar or nullptr if initialization failed.
LLAMA_API struct llama_grammar * llama_grammar_init(
const llama_grammar_element ** rules,
size_t n_rules,