update

llm/llama.cpp/common/common.cpp

@@ -2110,9 +2110,21 @@ struct llama_init_result llama_init_from_gpt_params(gpt_params & params) {
         loaded_la.adapter = llama_lora_adapter_init(model, la.path.c_str());
         if (loaded_la.adapter == nullptr) {
             fprintf(stderr, "%s: error: failed to apply lora adapter '%s'\n", __func__, la.path.c_str());
+
+            // if that fails, try loading as ggla for compatibility
+            int err = llama_model_apply_lora_from_file(model,
+                                                    la.path.c_str(),
+                                                    la.scale,
+                                                    nullptr,
+                                                    params.n_threads);
+            if (err != 0) {
+                fprintf(stderr, "%s: error: failed to apply lora adapter\n", __func__);
                 llama_free(lctx);
                 llama_free_model(model);
                 return iparams;
+            } else {
+                break;
+            }
         }
         iparams.lora_adapters.push_back(loaded_la); // copy to list of loaded adapters
     }
@@ -2178,6 +2190,8 @@ struct llama_model_params llama_model_params_from_gpt_params(const gpt_params &
     mparams.use_mmap        = params.use_mmap;
     mparams.use_mlock       = params.use_mlock;
     mparams.check_tensors   = params.check_tensors;
+    mparams.progress_callback = params.progress_callback;
+    mparams.progress_callback_user_data = params.progress_callback_user_data;
     if (params.kv_overrides.empty()) {
         mparams.kv_overrides = NULL;
     } else {

llm/llama.cpp/common/common.h

@@ -194,6 +194,13 @@ struct gpt_params {
     std::string mmproj = "";        // path to multimodal projector
     std::vector<std::string> image; // path to image file(s)
 
+    // Called with a progress value between 0.0 and 1.0. Pass NULL to disable.
+    // If the provided progress_callback returns true, model loading continues.
+    // If it returns false, model loading is immediately aborted.
+    llama_progress_callback progress_callback = NULL;
+    // context pointer passed to the progress callback
+    void * progress_callback_user_data;
+
     // embedding
     bool embedding         = false; // get only sentence embedding
     int32_t embd_normalize = 2;     // normalisation for embendings (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm)