vision : use --image parameter for vision example

danbev · Nov 11, 2024 · df21797 · df21797
1 parent 3cb6096
commit df21797
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 3 deletions.
diff --git a/common/arg.cpp b/common/arg.cpp
@@ -1394,7 +1394,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         [](common_params & params, const std::string & value) {
             params.image.emplace_back(value);
         }
-    ).set_examples({LLAMA_EXAMPLE_LLAVA}));
+    ).set_examples({LLAMA_EXAMPLE_LLAVA, LLAMA_EXAMPLE_VISION}));
     if (llama_supports_rpc()) {
         add_opt(common_arg(
             {"--rpc"}, "SERVERS",

diff --git a/common/common.h b/common/common.h
@@ -80,6 +80,7 @@ enum llama_example {
     LLAMA_EXAMPLE_PARALLEL,
 
     LLAMA_EXAMPLE_COUNT,
+    LLAMA_EXAMPLE_VISION,
 };
 
 enum common_sampler_type {

diff --git a/examples/vision/vision.cpp b/examples/vision/vision.cpp
@@ -20,7 +20,7 @@ int main(int argc, char ** argv) {
         "USER:<img_placement>\nwhat did you see?\nASSISTANT:";
     params.n_predict = 32;
 
-    if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_COMMON, print_usage)) {
+    if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_VISION, print_usage)) {
         return 1;
     }
 
@@ -98,7 +98,7 @@ int main(int argc, char ** argv) {
 
     // load image
     llama_batch_img img_batch = llama_batch_img_init(1);
-    img_batch.imgs[0] = load_image_from_file("models/eiffel-tower-3349075_1280.jpg");
+    img_batch.imgs[0] = load_image_from_file(params.image[0].c_str());
 
     // create a llama_batch with size 512
     // we use this object to submit token data for decoding