# Lab 1 - Generative AI Use Case: Dataset won't download

**URL:** <https://community.deeplearning.ai/t/lab-1-generative-ai-use-case-dataset-wont-download/698928>\
**Category:** Generative AI with Large Language Models\
**Tags:** lab-help, week-module-1\
**Created:** [September 27, 2024, 2:55am UTC](https://community.deeplearning.ai/t/lab-1-generative-ai-use-case-dataset-wont-download/698928 "2024-09-27T02:55:53Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![jaek](https://avatars.discourse-cdn.com/v4/letter/j/53a042/32.png) [@jaek](https://community.deeplearning.ai/u/jaek)\
**Post date:** [September 27, 2024, 2:55am UTC](https://community.deeplearning.ai/t/lab-1-generative-ai-use-case-dataset-wont-download/698928/1 "2024-09-27T02:55:53Z")

</div>

Week 1 Lab 1  
**Lab\_1\_summarize\_dialogue.ipynb**

This cell won’t work and fails due to timing out.  
I have rerun all the prior (4) cells and done so again after restarting the kernel.

**huggingface\_dataset\_name = “knkarthick/dialogsum”**  
**dataset = load\_dataset(huggingface\_dataset\_name)**

No data is downloaded so the lab is stuck at the preparation step.  
The error message is quite long. Here is the start of it.

TimeoutError Traceback (most recent call last)  
File /opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py:467, in HTTPConnectionPool.\_make\_request(self, conn, method, url, body, headers, retries, timeout, chunked, response\_conn, preload\_content, decode\_content, enforce\_content\_length)  
466 try:  
 → 467 self.\_validate\_conn(conn)  
468 except (SocketTimeout, BaseSSLError) as e:

File /opt/conda/lib/python3.10/site-packages/urllib3/connectionpool.py:1099, in HTTPSConnectionPool.\_validate\_conn(self, conn)  
1098 if conn.is\_closed:  
 → 1099 conn.connect()  
1101 # TODO revise this, see [Emit a warning when proxy\_is\_verified is False · Issue #2791 · urllib3/urllib3 · GitHub](https://github.com/urllib3/urllib3/issues/2791)

 ![image](https://global.discourse-cdn.com/dlai/original/3X/4/a/4a2478e9561c4d63a915c22af93ffd1ca04460d9.jpeg)

---

<div class="post-metadata">

**Author:** ![Anna\_Kay](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/anna_kay/32/94763_2.png) [@Anna\_Kay](https://community.deeplearning.ai/u/Anna_Kay)\
**Post date:** [September 27, 2024, 8:51am UTC](https://community.deeplearning.ai/t/lab-1-generative-ai-use-case-dataset-wont-download/698928/2 "2024-09-27T08:51:55Z")

</div>

Hello @jaek,

it is a general issue and is being looked into:

> [@Week 2 : Lab Assignment : Issue in loading HuggingFace](https://community.deeplearning.ai/t/week-2-lab-assignment-issue-in-loading-huggingface/698368):
>
> Hi Team, I am facing the below issue, tried it multiple times since yesterday: ReadTimeout: (ReadTimeoutError(“HTTPSConnectionPool(host=‘[cdn-lfs.hf.co](http://cdn-lfs.hf.co)’, port=443): Read timed out. (read timeout=10)”), ‘(Request ID: b5ad8989-819e-40e1-9f4c-3ba3b11614f7)’) when running the code: Can someone please guide or solve the issue? Thank you!
