Transformers
English
llama

Won't load on text-generation-webui

#1
by uti24 - opened

When I try loading saily_220b.Q3_K_M.gguf using text-generation-webui I got error:
Traceback (most recent call last):

File "S:\text-generation-webui\modules\ui_model_menu.py", line 214, in load_model_wrapper

shared.model, shared.tokenizer = load_model(selected_model, loader)

                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "S:\text-generation-webui\modules\models.py", line 90, in load_model

output = load_func_maploader

     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "S:\text-generation-webui\modules\models.py", line 260, in llamacpp_loader

model, tokenizer = LlamaCppModel.from_pretrained(model_file)

               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "S:\text-generation-webui\modules\llamacpp_model.py", line 101, in from_pretrained

result.model = Llama(**params)

           ^^^^^^^^^^^^^^^

File "S:\text-generation-webui\installer_files\env\Lib\site-packages\llama_cpp_cuda\llama.py", line 932, in init

self._ctx = _LlamaContext(

        ^^^^^^^^^^^^^^

File "S:\text-generation-webui\installer_files\env\Lib\site-packages\llama_cpp_cuda\llama.py", line 420, in init

self.ctx = llama_cpp.llama_new_context_with_model(

       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "S:\text-generation-webui\installer_files\env\Lib\site-packages\llama_cpp_cuda\llama_cpp.py", line 667, in llama_new_context_with_model

return _lib.llama_new_context_with_model(model, params)

   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

OSError: exception: access violation reading 0x0000000000000000

Sign up or log in to comment