# Cannot Login to HF

**URL:** <https://discuss.huggingface.co/t/cannot-login-to-hf/167787>\
**Category:** 🤗Transformers\
**Created:** [August 26, 2025, 7:00pm UTC](https://discuss.huggingface.co/t/cannot-login-to-hf/167787 "2025-08-26T19:00:09Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![samerkhamaiseh](https://avatars.discourse-cdn.com/v4/letter/s/4491bb/32.png) [@samerkhamaiseh](https://discuss.huggingface.co/u/samerkhamaiseh)\
**Post date:** [August 26, 2025, 7:00pm UTC](https://discuss.huggingface.co/t/cannot-login-to-hf/167787/1 "2025-08-26T19:00:09Z")

</div>

Hello Everyone:

I am having a problem logging to HF hub, despite I have access token with valid gated access and have accepted all the agreements. However, still waiting to get approved for LLAMA-3.2-1B-Instruct.

Problem steps:

1- cannot access and the showing the following error despite that I am not using Llama-3.2-1B-Instruct in my code.

“

“Model trl-internal-testing/tiny-BloomForCausalLM already exists, skipping  
Model trl-internal-testing/tiny-CohereForCausalLM already exists, skipping  
Model trl-internal-testing/tiny-DbrxForCausalLM already exists, skipping  
Model trl-internal-testing/tiny-DeepseekV3ForCausalLM already exists, skipping”

cannot access gated repo for url [https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/resolve/main/config.json).  
Access to model meta-llama/Llama-3.2-1B-Instruct is restricted. You must have access to it and be authenticated to access it. Please log in.”

– I tried CLI login and login from the source code using the token, nothing works

Please share your thoughts here.

---

<div class="post-metadata">

**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:** [August 26, 2025, 11:36pm UTC](https://discuss.huggingface.co/t/cannot-login-to-hf/167787/2 "2025-08-26T23:36:25Z")

</div>

[LLAMA-3.2-1B-Instruct is a manual-approved gated model](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/discussions), so the approval process takes time. It may also be rejected. Therefore, it is normal for it to be [inaccessible if approval is pending](https://huggingface.co/docs/hub/models-gated).

If only the model weights are sufficient for your use case, [searching on the Hub](https://huggingface.co/models?pipeline_tag=text-generation&library=transformers&sort=trending&search=LLAMA-3.2-1B-Instruct) maybe faster option.