# Dummy\_agent\_library.ipynb not working for me **URL:** \ **Category:** Course\ **Created:** [May 6, 2025, 6:14pm UTC](https://discuss.huggingface.co/t/dummy-agent-library-ipynb-not-working-for-me/153795 "2025-05-06T18:14:24Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![shafaat](https://avatars.discourse-cdn.com/v4/letter/s/8dc957/32.png) [@shafaat](https://discuss.huggingface.co/u/shafaat)\ **Post date:** [May 6, 2025, 6:14pm UTC](https://discuss.huggingface.co/t/dummy-agent-library-ipynb-not-working-for-me/153795/1 "2025-05-06T18:14:24Z")
Hi This may sound dumb, but I am not able to get the output for cell 3 of the dummy\_agent\_library.ipynb. I am getting the error “Invalid credentials in Authorization header”. I already have access to the Meta Llama models. I have tested the model with read and write tokens. I have copied these tokens in the secret as well as in cell 2. I have also tried #client = InferenceClient(“[https://jc26mwg228mkj8dw.us-east-1.aws.endpoints.huggingface.cloud](https://jc26mwg228mkj8dw.us-east-1.aws.endpoints.huggingface.cloud)”) But nothing is working for me ---
**Author:** ![shafaat](https://avatars.discourse-cdn.com/v4/letter/s/8dc957/32.png) [@shafaat](https://discuss.huggingface.co/u/shafaat)\ **Post date:** [May 6, 2025, 7:05pm UTC](https://discuss.huggingface.co/t/dummy-agent-library-ipynb-not-working-for-me/153795/2 "2025-05-06T19:05:15Z")
This is the complete error HTTPError Traceback (most recent call last) /usr/local/lib/python3.11/dist-packages/huggingface\_hub/utils/\_http.py in hf\_raise\_for\_status(response, endpoint\_name) 408 try: → 409 response.raise\_for\_status() 410 except HTTPError as e: 6 frames HTTPError: 401 Client Error: Unauthorized for url: [https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3.2-3B-Instruct](https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3.2-3B-Instruct) The above exception was the direct cause of the following exception: HfHubHTTPError Traceback (most recent call last) /usr/local/lib/python3.11/dist-packages/huggingface\_hub/utils/\_http.py in hf\_raise\_for\_status(response, endpoint\_name) 480 # Convert `HTTPError` into a `HfHubHTTPError` to display request information 481 # as well (request id and/or server error message) → 482 raise \_format(HfHubHTTPError, str(e), response) from e 483 484 HfHubHTTPError: 401 Client Error: Unauthorized for url: [https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3.2-3B-Instruct](https://router.huggingface.co/hf-inference/models/meta-llama/Llama-3.2-3B-Instruct) (Request ID: Root=1-681a5d47-07dc05de5cc5d36a3bdf2179;2ff8c0a3-3b5d-404c-862d-6b6fbad084bd) Invalid credentials in Authorization header ---
**Author:** ![ArchonzCrz](https://avatars.discourse-cdn.com/v4/letter/a/90db22/32.png) [@ArchonzCrz](https://discuss.huggingface.co/u/ArchonzCrz)\ **Post date:** [May 7, 2025, 12:58am UTC](https://discuss.huggingface.co/t/dummy-agent-library-ipynb-not-working-for-me/153795/3 "2025-05-07T00:58:38Z")
Same for me. I went to the inference endpoint. Seems like the Llama model is not deployed there. ---
**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:** [May 7, 2025, 1:59am UTC](https://discuss.huggingface.co/t/dummy-agent-library-ipynb-not-working-for-me/153795/4 "2025-05-07T01:59:32Z")
Currently, many models are in a non-deploy state. > [@Inference API stopped working](https://discuss.huggingface.co/t/inference-api-stopped-working/150492): > > Hi everyone, I seem to be encountering a sudden issue with the Hugging Face Inference API. I was successfully using it for image-to-image tasks (specifically with models like stabilityai/stable-diffusion-xl-refiner-1.0), but it abruptly stopped working a short while ago. Now, regardless of which model I try to use, I consistently receive the following error pattern: Model \ is not supported HF inference api This is happening in two distinct ways: Via InferenceClient: My applicat… ---
**Author:** ![ccccaaattthhhyyy](https://avatars.discourse-cdn.com/v4/letter/c/f17d59/32.png) [@ccccaaattthhhyyy](https://discuss.huggingface.co/u/ccccaaattthhhyyy)\ **Post date:** [July 3, 2025, 4:50am UTC](https://discuss.huggingface.co/t/dummy-agent-library-ipynb-not-working-for-me/153795/5 "2025-07-03T04:50:19Z")
I have a different error, “504 Server Error: Gateway Time-out”. But yeah, I can’t complete this exercise. ---
**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:** [July 3, 2025, 5:43am UTC](https://discuss.huggingface.co/t/dummy-agent-library-ipynb-not-working-for-me/153795/6 "2025-07-03T05:43:59Z")
Try alternative methods. > [@Are InferenceClient()'s down?](https://discuss.huggingface.co/t/are-inferenceclient-s-down/161485/10): > > use: provider=“together” for mistralai models.. > [@You have exceeded your monthly included credits for Inference Providers](https://discuss.huggingface.co/t/you-have-exceeded-your-monthly-included-credits-for-inference-providers/161349/2): > > There are quite a few alternatives available, including local models. Gemini also seems to be available via LiteLLM.