Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/build.yml
#	CMakeLists.txt
#	README.md
#	ci/run.sh
#	llama.cpp
#	models/ggml-vocab-llama-bpe.gguf.inp
#	models/ggml-vocab-llama-bpe.gguf.out
#	requirements.txt
#	scripts/compare-llama-bench.py
#	scripts/sync-ggml.last
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-tokenizer-1-bpe.cpp
This commit is contained in:
Concedo 2024-05-14 19:28:47 +08:00
commit 2ee808a747
66 changed files with 3034 additions and 1821 deletions

View file

@ -902,6 +902,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.interactive = true;
return true;
}
if (arg == "--interactive-specials") {
params.interactive_specials = true;
return true;
}
if (arg == "--embedding") {
params.embedding = true;
return true;
@ -1368,14 +1372,12 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) {
if (arg.compare(0, arg_prefix.size(), arg_prefix) == 0) {
std::replace(arg.begin(), arg.end(), '_', '-');
}
if (!gpt_params_find_arg(argc, argv, arg, params, i, invalid_param)) {
throw std::invalid_argument("error: unknown argument: " + arg);
}
}
if (invalid_param) {
throw std::invalid_argument("error: invalid parameter for argument: " + arg);
if (invalid_param) {
throw std::invalid_argument("error: invalid parameter for argument: " + arg);
}
}
if (params.prompt_cache_all &&
@ -1423,6 +1425,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" -h, --help show this help message and exit\n");
printf(" --version show version and build info\n");
printf(" -i, --interactive run in interactive mode\n");
printf(" --interactive-specials allow special tokens in user text, 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");
@ -2653,6 +2656,7 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l
dump_string_yaml_multiline(stream, "in_suffix", params.input_prefix.c_str());
fprintf(stream, "instruct: %s # default: false\n", params.instruct ? "true" : "false");
fprintf(stream, "interactive: %s # default: false\n", params.interactive ? "true" : "false");
fprintf(stream, "interactive_specials: %s # default: false\n", params.interactive_specials ? "true" : "false");
fprintf(stream, "interactive_first: %s # default: false\n", params.interactive_first ? "true" : "false");
fprintf(stream, "keep: %d # default: 0\n", params.n_keep);
fprintf(stream, "logdir: %s # default: unset (no logging)\n", params.logdir.c_str());