# Inference Issue with Llama Models using HF Inference **URL:** \ **Category:** Beginners\ **Created:** [February 5, 2025, 10:00pm UTC](https://discuss.huggingface.co/t/inference-issue-with-llama-models-using-hf-inference/139207 "2025-02-05T22:00:17Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![batharun2](https://avatars.discourse-cdn.com/v4/letter/b/a88e4f/32.png) [@batharun2](https://discuss.huggingface.co/u/batharun2)\ **Post date:** [February 5, 2025, 10:00pm UTC](https://discuss.huggingface.co/t/inference-issue-with-llama-models-using-hf-inference/139207/1 "2025-02-05T22:00:17Z")
Hello All, Please pardon for my basic/trivial questions, still i am in learning phase. Context: I used Autotrain to train meta-llama/Llama-3.2-1B (i have access to this model). Autrain completed succesfully. I want to test using HF Inference Endpoint option available from fine tuned model. I am getting following error and not sure how to resolve this issue. Appreciate your help on this. Thank you! ==============error================ Exit code: 3. Reason: File “/app/huggingface\_inference\_toolkit/handler.py”, line 22, in **init** self.pipeline = get\_pipeline( ^^^^^^^^^^^^^ File “/app/huggingface\_inference\_toolkit/utils.py”, line 252, in get\_pipeline hf\_pipeline = pipeline(task=task, model=model\_dir, device=device, \*\*kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File “/usr/local/lib/python3.11/dist-packages/transformers/pipelines/ **init**.py”, line 849, in pipeline config = AutoConfig.from\_pretrained( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File “/usr/local/lib/python3.11/dist-packages/transformers/models/auto/configuration\_auto.py”, line 1054, in from\_pretrained config\_dict, unused\_kwargs = PretrainedConfig.get\_config\_dict(pretrained\_model\_name\_or\_path, \*\*kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File “/usr/local/lib/python3.11/dist-packages/transformers/configuration\_utils.py”, line 591, in get\_config\_dict config\_dict, kwargs = cls.\_get\_config\_dict(pretrained\_model\_name\_or\_path, \*\*kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File “/usr/local/lib/python3.11/dist-packages/transformers/configuration\_utils.py”, line 650, in \_get\_config\_dict resolved\_config\_file = cached\_file( ^^^^^^^^^^^^ File “/usr/local/lib/python3.11/dist-packages/transformers/utils/hub.py”, line 421, in cached\_file raise EnvironmentError( OSError: You are trying to access a gated repo. Make sure to have access to it at [meta-llama/Llama-3.2-1B · Hugging Face](https://huggingface.co/meta-llama/Llama-3.2-1B). 401 Client Error. (Request ID: Root=1-67a3db7b-5d79316f2004d07c068598e2;57232df2-b5bf-4ca0-b882-4b0a4cfc1100) Cannot access gated repo for url [https://huggingface.co/meta-llama/Llama-3.2-1B/resolve/main/config.json](https://huggingface.co/meta-llama/Llama-3.2-1B/resolve/main/config.json). Access to model meta-llama/Llama-3.2-1B is restricted. You must have access to it and be authenticated to access it. Please log in. Application startup failed. Exiting. ---
**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\ **Post date:** [February 6, 2025, 6:37am UTC](https://discuss.huggingface.co/t/inference-issue-with-llama-models-using-hf-inference/139207/2 "2025-02-06T06:37:19Z")
When loading a trained model (difference), it seems that an error occurs because it needs to refer to the original model. In short, it can be fixed by passing a token. There are several ways to do this, such as passing it directly with **token=** or executing **login()** in advance. > **[User access tokens](https://huggingface.co/docs/hub/security-tokens)** > > We’re on a journey to advance and democratize artificial intelligence through open source and open science. > **[Quickstart](https://huggingface.co/docs/huggingface_hub/main/quick-start#authentication)** > > We’re on a journey to advance and democratize artificial intelligence through open source and open science.