Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	README.md
#	examples/gbnf-validator/gbnf-validator.cpp
#	examples/llava/clip.cpp
#	examples/run/README.md
#	examples/run/run.cpp
#	examples/server/README.md
#	ggml/src/ggml-cpu/CMakeLists.txt
#	src/llama.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-llama-grammar.cpp
This commit is contained in:
Concedo 2024-12-21 09:41:49 +08:00
commit 4c56b7cada
19 changed files with 550 additions and 226 deletions

View file

@ -627,7 +627,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.ctx_shift = false;
}
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_IMATRIX}).set_env("LLAMA_ARG_NO_CONTEXT_SHIFT"));
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_PERPLEXITY}).set_env("LLAMA_ARG_NO_CONTEXT_SHIFT"));
add_opt(common_arg(
{"--chunks"}, "N",
string_format("max number of chunks to process (default: %d, -1 = all)", params.n_chunks),
@ -2207,5 +2207,17 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples({LLAMA_EXAMPLE_TTS, LLAMA_EXAMPLE_SERVER}));
// model-specific
add_opt(common_arg(
{"--tts-oute-default"},
string_format("use default OuteTTS models (note: can download weights from the internet)"),
[](common_params & params) {
params.hf_repo = "OuteAI/OuteTTS-0.2-500M-GGUF";
params.hf_file = "OuteTTS-0.2-500M-Q8_0.gguf";
params.vocoder.hf_repo = "ggml-org/WavTokenizer";
params.vocoder.hf_file = "WavTokenizer-Large-75-F16.gguf";
}
).set_examples({LLAMA_EXAMPLE_TTS}));
return ctx_arg;
}