vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	CMakeLists.txt
#	Makefile
#	README.md
#	common/common.cpp
#	requirements/requirements-convert-hf-to-gguf-update.txt
#	requirements/requirements-convert-hf-to-gguf.txt
#	requirements/requirements-convert.txt
#	tests/CMakeLists.txt
#	tests/test-json-schema-to-grammar.cpp
This commit is contained in:
Concedo 2024-05-09 15:13:34 +08:00
commit d084f78faa
48 changed files with 3786 additions and 1438 deletions
Download patch file Download diff file Expand all files Collapse all files

19
common/common.cpp
View file

@ -1,5 +1,7 @@
#include "common.h"
#include "build-info.h"
// Change JSON_ASSERT from assert() to GGML_ASSERT:
#define JSON_ASSERT GGML_ASSERT
#include "json.hpp"
#include "json-schema-to-grammar.h"
#include "llama.h"
@ -912,6 +914,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.instruct = true;
return true;
}
if (arg == "-cnv" || arg == "--conversation") {
params.conversation = true;
return true;
}
if (arg == "-cml" || arg == "--chatml") {
params.chatml = true;
return true;
@ -1418,6 +1424,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" --version show version and build info\n");
printf(" -i, --interactive run in interactive mode\n");
printf(" --interactive-first run in interactive mode and wait for input right away\n");
printf(" -cnv, --conversation run in conversation mode (does not print special tokens and suffix/prefix)\n");
printf(" -ins, --instruct run in instruction mode (use with Alpaca models)\n");
printf(" -cml, --chatml run in chatml mode (use with ChatML-compatible models)\n");
printf(" --multiline-input allows you to write or paste multiple lines without ending each in '\\'\n");
@ -1965,18 +1972,18 @@ static bool llama_download_file(const std::string & url, const std::string & pat
try {
metadata_in >> metadata;
fprintf(stderr, "%s: previous metadata file found %s: %s\n", __func__, metadata_path.c_str(), metadata.dump().c_str());
if (metadata.contains("url") && metadata["url"].is_string()) {
auto previous_url = metadata["url"].get<std::string>();
if (metadata.contains("url") && metadata.at("url").is_string()) {
auto previous_url = metadata.at("url").get<std::string>();
if (previous_url != url) {
fprintf(stderr, "%s: Model URL mismatch: %s != %s\n", __func__, url.c_str(), previous_url.c_str());
return false;
}
}
if (metadata.contains("etag") && metadata["etag"].is_string()) {
etag = metadata["etag"];
if (metadata.contains("etag") && metadata.at("etag").is_string()) {
etag = metadata.at("etag");
}
if (metadata.contains("lastModified") && metadata["lastModified"].is_string()) {
last_modified = metadata["lastModified"];
if (metadata.contains("lastModified") && metadata.at("lastModified").is_string()) {
last_modified = metadata.at("lastModified");
}
} catch (const nlohmann::json::exception & e) {
fprintf(stderr, "%s: error reading metadata file %s: %s\n", __func__, metadata_path.c_str(), e.what());