merged llama adapter into the rest of the gpt adapters

expose.cpp

@@ -118,20 +118,20 @@ extern "C"
         else
         {
             printf("\n---\nIdentified as LLAMA model: (ver %d)\nAttempting to Load...\n---\n", file_format);
-            return llama_load_model(inputs, file_format);
+            ModelLoadResult lr = gpttype_load_model(inputs, file_format);
+            if (lr == ModelLoadResult::FAIL || lr == ModelLoadResult::RETRY_LOAD)
+            {
+                return false;
+            }
+            else
+            {
+                return true;
+            }
         }
     }
 
     generation_outputs generate(const generation_inputs inputs, generation_outputs &output)
     {
-        if (file_format == FileFormat::GPTJ_1 || file_format == FileFormat::GPTJ_2 || file_format==FileFormat::GPTJ_3
-        || file_format==FileFormat::GPT2_1 || file_format==FileFormat::GPT2_2 || file_format==FileFormat::RWKV_1)
-        {
-            return gpttype_generate(inputs, output);
-        }
-        else
-        {
-            return llama_generate(inputs, output);
-        }
+        return gpttype_generate(inputs, output);
     }
 }