expose n_gpu_layers parameter of llama.cpp (#1890)

Also dynamically limit the GPU layers and context length fields to the maximum supported by the model.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

gpt4all-bindings/golang/binding.cpp

@@ -23,7 +23,7 @@ void* load_model(const char *fname, int n_threads) {
         fprintf(stderr, "%s: error '%s'\n", __func__, new_error);
         return nullptr;
     }
-    if (!llmodel_loadModel(model, fname, 2048)) {
+    if (!llmodel_loadModel(model, fname, 2048, 100)) {
         llmodel_model_destroy(model);
         return nullptr;
     }