diff options
| author | cpumaxx <163466046+cpumaxx@users.noreply.github.com> | 2024-04-29 07:34:24 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-29 17:34:24 +0300 |
| commit | ffe666572f98a686b17a2cd1dbf4c0a982e5ac0a (patch) | |
| tree | 062ed2b2706163cdb2006b0204c4589e7da4f75a /common | |
| parent | 24affa7db3c9db148854b0ab4fd63de8bca7d898 (diff) | |
llava-cli : multiple images (#6969)
Co-authored-by: root <root@nenya.lothlorien.ca>
Diffstat (limited to 'common')
| -rw-r--r-- | common/common.cpp | 4 | ||||
| -rw-r--r-- | common/common.h | 4 |
2 files changed, 4 insertions, 4 deletions
diff --git a/common/common.cpp b/common/common.cpp index aa494291..fe84039f 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -893,7 +893,7 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa invalid_param = true; return true; } - params.image = argv[i]; + params.image.emplace_back(argv[i]); return true; } if (arg == "-i" || arg == "--interactive") { @@ -1495,7 +1495,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) { printf(" -ps N, --p-split N speculative decoding split probability (default: %.1f)\n", (double)params.p_split); printf(" -cb, --cont-batching enable continuous batching (a.k.a dynamic batching) (default: disabled)\n"); printf(" --mmproj MMPROJ_FILE path to a multimodal projector file for LLaVA. see examples/llava/README.md\n"); - printf(" --image IMAGE_FILE path to an image file. use with multimodal models\n"); + printf(" --image IMAGE_FILE path to an image file. use with multimodal models. Specify multiple times for batching\n"); if (llama_supports_mlock()) { printf(" --mlock force system to keep model in RAM rather than swapping or compressing\n"); } diff --git a/common/common.h b/common/common.h index eea63a11..3233d90e 100644 --- a/common/common.h +++ b/common/common.h @@ -167,8 +167,8 @@ struct gpt_params { std::string cache_type_v = "f16"; // KV cache data type for the V // multimodal models (see examples/llava) - std::string mmproj = ""; // path to multimodal projector - std::string image = ""; // path to an image file + std::string mmproj = ""; // path to multimodal projector + std::vector<std::string> image; // path to image file(s) }; bool parse_kv_override(const char * data, std::vector<llama_model_kv_override> & overrides); |