Getting error with LLama2 and LLama3 based AWQ models. #462
Unanswered
alok-abhishek
asked this question in
Q&A
Replies: 1 comment
-
Having the same issue. I think it's some issue with certain 13B AWQ models because GGUF models and x<7B AWQ models work. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
AttributeError: 'LlamaLikeModel' object has no attribute 'layers'
Traceback (most recent call last):
File "inference\awq\inference_awq_hf.py", line 50, in
generation_output = model.generate(
^^^^^^^^^^^^^^^
File ".venv\Lib\site-packages\awq\models\base.py", line 111, in generate
return self.model.generate(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".venv\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File ".venv\Lib\site-packages\transformers\generation\utils.py", line 1622, in generate
result = self._sample(
^^^^^^^^^^^^^
File ".venv\Lib\site-packages\transformers\generation\utils.py", line 2788, in _sample
model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".venv\Lib\site-packages\transformers\models\llama\modeling_llama.py", line 1262, in prepare_inputs_for_generation
past_key_values = getattr(getattr(self.model.layers[0], "self_attn", {}), "past_key_value", None)
^^^^^^^^^^^^^^^^^
File ".venv\Lib\site-packages\torch\nn\modules\module.py", line 1688, in getattr
raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")
AttributeError: 'LlamaLikeModel' object has no attribute 'layers'
I also saw the same issue report here: oobabooga_text-generation-webui_issues_5778
Beta Was this translation helpful? Give feedback.
All reactions