# Accessing SciBERT Model

**URL:** <https://discuss.huggingface.co/t/accessing-scibert-model/76039>\
**Category:** Beginners\
**Created:** [March 5, 2024, 3:39pm UTC](https://discuss.huggingface.co/t/accessing-scibert-model/76039 "2024-03-05T15:39:22Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![kawshikbanerjee2024](https://avatars.discourse-cdn.com/v4/letter/k/e0b2c6/32.png) [@kawshikbanerjee2024](https://discuss.huggingface.co/u/kawshikbanerjee2024)\
**Post date:** [March 5, 2024, 3:39pm UTC](https://discuss.huggingface.co/t/accessing-scibert-model/76039/1 "2024-03-05T15:39:22Z")

</div>

Hi everyone,  
I’m a complete beginner in using the Huggingface model. I’m trying to use the SciBERT model in Google Colab for an ablation study this way:

```auto
model_name = "allenai/scibert_base_uncased/tree/main"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2)

```

I am using a secret key in my colab session with ‘read’ access. But getting this error:

> HFValidationError: Repo id must be in the form ‘repo\_name’ or ‘namespace/repo\_name’: ‘allenai/scibert\_base\_uncased/tree/main’. Use `repo_type` argument if needed.

Can someone please specify what am I doing wrong here and how can I access the model? Also, any resource on how to do ablation on text data would be really appreciated. Thanks in advance.

---

<div class="post-metadata">

**Author:** ![chungimungi](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/chungimungi/32/24565_2.png) [@chungimungi](https://discuss.huggingface.co/u/chungimungi)\
**Post date:** [March 7, 2024, 8:27am UTC](https://discuss.huggingface.co/t/accessing-scibert-model/76039/2 "2024-03-07T08:27:18Z")

</div>

I can not find the exact model but here is a possible fix.

```auto
model_name = "allenai/scibert_scivocab_uncased"

```

You dont need to pass **/tree/main** in the string for the model name.