).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_CONT_BATCHING"));
add_opt(common_arg(
{"--mmproj"}, "FILE",
- "path to a multimodal projector file. see tools/mtmd/README.md",
+ "path to a multimodal projector file. see tools/mtmd/README.md\n"
+ "note: if -hf is used, this argument can be omitted",
[](common_params & params, const std::string & value) {
params.mmproj.path = value;
}
- ).set_examples(mmproj_examples));
+ ).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ"));
add_opt(common_arg(
{"--mmproj-url"}, "URL",
"URL to a multimodal projector file. see tools/mtmd/README.md",
[](common_params & params, const std::string & value) {
params.mmproj.url = value;
}
- ).set_examples(mmproj_examples));
+ ).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ_URL"));
add_opt(common_arg(
{"--no-mmproj"},
"explicitly disable multimodal projector, useful when using -hf",
[](common_params & params) {
params.no_mmproj = true;
}
- ).set_examples(mmproj_examples));
+ ).set_examples(mmproj_examples).set_env("LLAMA_ARG_NO_MMPROJ"));
add_opt(common_arg(
{"--no-mmproj-offload"},
"do not offload multimodal projector to GPU",
[](common_params & params) {
params.mmproj_use_gpu = false;
}
- ).set_examples(mmproj_examples));
+ ).set_examples(mmproj_examples).set_env("LLAMA_ARG_NO_MMPROJ_OFFLOAD"));
add_opt(common_arg(
{"--image"}, "FILE",
"path to an image file. use with multimodal models. Specify multiple times for batching",