rasbt/LLMs-from-scratchPublic

NotificationsYou must be signed in to change notification settings
Fork12k
Star80.3k

Alternative`gpt2` weight download#273

rasbt started this conversation inGeneral

Alternative `gpt2` weight download#273

rasbt

Jul 19, 2024

· 8 comments· 7 replies

Return to top

Discussion options

rasbt
Jul 19, 2024
Maintainer

In case the official weights from OpenAI ever become unavailable, I wanted to share a few tips for working around the issue.

1) Connection checks

It could be a temporary internet connection issue or a problem with your IP address. I recommend double-checking using a different machine (e.g., Google Colab).

For your convenience, use the following code to download the download script and the GPT-2 weights:

# Download the download fileimporturllib.requesturl= ("https://raw.githubusercontent.com/rasbt/""LLMs-from-scratch/main/ch05/""01_main-chapter-code/gpt_download.py")filename=url.split("/")[-1]urllib.request.urlretrieve(url,filename)

fromgpt_downloadimportdownload_and_load_gpt2settings,params=download_and_load_gpt2(model_size="124M",models_dir="gpt2")# settings, params = download_and_load_gpt2(model_size="355M", models_dir="gpt2")# settings, params = download_and_load_gpt2(model_size="774M", models_dir="gpt2")# settings, params = download_and_load_gpt2(model_size="1558M", models_dir="gpt2")

2) Alternative download

In case the above doesn't work, you can download the weights from this alternative linkhere.

Click on "Download" to download the respective weights.

Then,

Create a folder calledgpt2 in the location where you are planning to execute the code for loading the weights
Move the downloaded zip file into thisgpt2 folder
Load the weights using the code shared in section 1 above

3) Alternative weight loading

In case you are still having problems, for example, because of a TensorFlow incompatibility (the original weights were stored as TensorFlow tensors. Hence, we need TensorFlow for the weight conversion to PyTorch), considerthis alternative way of loading the weights from the Hugging Face Hub.

You must be logged in to vote

Replies: 8 comments 7 replies

Comment options

jms-dipadua
Dec 11, 2024

thank you for providing this alternative method. the option within the book wasn't working but Option 1 above did the trick :)

You must be logged in to vote

1 reply

Comment options

rasbt Dec 13, 2024
Maintainer Author

glad it helped!

Comment options

robertfo
Mar 2, 2025

I tried to do according to the book (section 5.5). Everything worked fine up to the command:

from gpt_download import download_and_load_gpt2
which gave the error message:
zsh: illegal hardware instruction python

Is there a simple cure? If not, I will try the proposed alternatives.

Versions

Apple M1 Pro
pip 24.0
tensorflow 2.16.2
python 3.12.4

You must be logged in to vote

1 reply

Comment options

rasbt Mar 2, 2025
Maintainer Author

hm, could you inspect thedownload_and_load_gpt2.py file and see if it maybe has malformed contents? And maybe try to replace it by downloading a fresh copy from here:https://github.com/rasbt/LLMs-from-scratch/blob/main/ch05/01_main-chapter-code/gpt_download.py

Comment options

robertfo
Mar 2, 2025

Hi Sebastian,Nice getting in touch again…The ”gpt_download.py” file looks ok. I have also tried with the fresh copy that you suggest. In both cases the python command ”from gpt_download_and_load_gpt2” causes the hardware error.Robert2 mars 2025 kl. 17:52 skrev Sebastian Raschka ***@***.***>:hm, could you inspect the download_and_load_gpt2.py file and see if it maybe has malformed contents? And maybe try to replace it by downloading a fresh copy from here:https://github.com/rasbt/LLMs-from-scratch/blob/main/ch05/01_main-chapter-code/gpt_download.py—Reply to this email directly, view it on GitHub<#273 (reply in thread)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AB5DKLBMYOOTZAEF3CPYW3T2SMZLJAVCNFSM6AAAAABLERIUGSVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTEMZWG4YTCMY>.You are receiving this because you commented.Message ID: ***@***.***>

You must be logged in to vote

1 reply

Comment options

rasbt Mar 2, 2025
Maintainer Author

Wow that's so weird. I have been using Python for ~14 years now and never seen anything like this.

I wonder what happens if you upload the file to Google Colab and run it there. Do you get the same error?
If not, maybe your version of Python has a compatibility issue?
Another thing worth trying: Could you copy and paste the contents of thegpt_download_and_load_gpt2.py directly into your script/notebook so that you can skip thefrom gpt_download_and_load_gpt2 import... and see if it still happens? Maybe it will help narrowing down where exactly in the code it happens.

Comment options

robertfo
Mar 2, 2025

The problem is that the file gpt_download_and_load_gpt2.py never loads due to the occuring error.Btw, are we talking about the same command? Below you mention "from gpt_download_and_load_gpt2 import…” while the book says "from gpt_download import….”?2 mars 2025 kl. 18:47 skrev Sebastian Raschka ***@***.***>:Wow that's so weird. I have been using Python for ~14 years now and never seen anything like this. 1. I wonder what happens if you upload the file to Google Colab and run it there. Do you get the same error?If not, maybe your version of Python has a compatibility issue? 2. Another thing worth trying: Could you copy and paste the contents of the gpt_download_and_load_gpt2.py directly into your script/notebook so that you can skip the from gpt_download_and_load_gpt2 import... and see if it still happens? Maybe it will help narrowing down where exactly in the code it happens.—Reply to this email directly, view it on GitHub<#273 (reply in thread)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AB5DKLB26BZMTTC2ULWFAL32SM72PAVCNFSM6AAAAABLERIUGSVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTEMZWG4ZTSMQ>.You are receiving this because you commented.Message ID: ***@***.***>

You must be logged in to vote

1 reply

Comment options

rasbt Mar 2, 2025
Maintainer Author

My apologies, yes, I meant the

from gpt_download import download_and_load_gpt2

command

Comment options

robertfo
Mar 2, 2025

I copied and pasted the contents of ”gpt_download.py” into my python script. The error occurs at the line "import tensorflow as tf”.2 mars 2025 kl. 18:59 skrev Robert Forchheimer ***@***.***>:The problem is that the file gpt_download_and_load_gpt2.py never loads due to the occuring error.Btw, are we talking about the same command? Below you mention "from gpt_download_and_load_gpt2 import…” while the book says "from gpt_download import….”?2 mars 2025 kl. 18:47 skrev Sebastian Raschka ***@***.***>:Wow that's so weird. I have been using Python for ~14 years now and never seen anything like this. 1. I wonder what happens if you upload the file to Google Colab and run it there. Do you get the same error?If not, maybe your version of Python has a compatibility issue? 2. Another thing worth trying: Could you copy and paste the contents of the gpt_download_and_load_gpt2.py directly into your script/notebook so that you can skip the from gpt_download_and_load_gpt2 import... and see if it still happens? Maybe it will help narrowing down where exactly in the code it happens.—Reply to this email directly, view it on GitHub<#273 (reply in thread)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AB5DKLB26BZMTTC2ULWFAL32SM72PAVCNFSM6AAAAABLERIUGSVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTEMZWG4ZTSMQ>.You are receiving this because you commented.Message ID: ***@***.***>

You must be logged in to vote

1 reply

Comment options

rasbt Mar 2, 2025
Maintainer Author

Hm, maybe there's been an issue with installingtensorflow on your computer. You could try to reinstall it via

pip uninstall -y tensorflow tensorflow-cpu tensorflow-gpu tensorflow-intelpip cache purge  # Clear any cached TensorFlow packagespip install --no-cache-dir tensorflow

If this still doesn't work, I do have alternative codes to load the weights without using TensorFlow. I just preferred this way in the book because these are the original and official weights provided by OpenAI.

The alternatives can be found here:https://github.com/rasbt/LLMs-from-scratch/tree/main/ch05/02_alternative_weight_loading

Comment options

robertfo
Mar 2, 2025

Thanks Sebastian, problem solved!I changed to another (conda) environment and installed tensorflow. That was sufficient.Robert2 mars 2025 kl. 19:54 skrev Sebastian Raschka ***@***.***>:Hm, maybe there's been an issue with installing tensorflow on your computer. You could try to reinstall it viapip uninstall -y tensorflow tensorflow-cpu tensorflow-gpu tensorflow-intelpip cache purge # Clear any cached TensorFlow packagespip install --no-cache-dir tensorflowIf this still doesn't work, I do have alternative codes to load the weights without using TensorFlow. I just preferred this way in the book because these are the original and official weights provided by OpenAI.The alternatives can be found here:https://github.com/rasbt/LLMs-from-scratch/tree/main/ch05/02_alternative_weight_loading—Reply to this email directly, view it on GitHub<#273 (reply in thread)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AB5DKLCKIEBDMYHQCJMS74D2SNHWFAVCNFSM6AAAAABLERIUGSVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTEMZWG43TKNQ>.You are receiving this because you commented.Message ID: ***@***.***>

You must be logged in to vote

1 reply

Comment options

rasbt Mar 2, 2025
Maintainer Author

I am glad you got it to work. I am adding a note (#555) about this to the code notebook in case someone else experiences similar issues.

Comment options

jms-dipadua
Mar 3, 2025

apologies for a delay. was away from the laptop for a bit there -- irecalled having a little issue with the download but navigating your githubrepo and getting the files directly helped.i directly downloaded your py file with the following:```import urllib.requesturl = ( "https://raw.githubusercontent.com/rasbt/" "LLMs-from-scratch/main/ch05/" "01_main-chapter-code/gpt_download.py")filename = url.split("/")[-1]urllib.request.urlretrieve(url, filename)```so that when i called the following it worked without any issues:```from gpt_download import download_and_load_gpt2settings, params = download_and_load_gpt2(model_size="355M",models_dir="gpt2")```

…

On Sun, Mar 2, 2025 at 1:12 PM Sebastian Raschka ***@***.***> wrote: I am glad you got it to work. I am adding a note (#555 <#555>) about this to the code notebook in case someone else experiences similar issues. — Reply to this email directly, view it on GitHub <#273 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAQCEVHIZSDNQN427IZZSUL2SNX3XAVCNFSM6AAAAABLERIUGSVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTEMZWHAZTQOA> . You are receiving this because you commented.Message ID: ***@***.*** com>

You must be logged in to vote

1 reply

Comment options

rasbt Mar 10, 2025
Maintainer Author

Glad you got it to work!

Comment options

Emma2297
May 21, 2025

Thanks for sharing!

You must be logged in to vote

0 replies

Movatterモバイル変換

Alternativegpt2 weight download#273

Uh oh!

rasbtJul 19, 2024 Maintainer

1) Connection checks

2) Alternative download

3) Alternative weight loading

Replies: 8 comments· 7 replies

Uh oh!

Uh oh!

rasbtDec 13, 2024 Maintainer Author

Uh oh!

Versions

Uh oh!

rasbtMar 2, 2025 Maintainer Author

Uh oh!

Uh oh!

rasbtMar 2, 2025 Maintainer Author

Uh oh!

Uh oh!

rasbtMar 2, 2025 Maintainer Author

Uh oh!

Uh oh!

rasbtMar 2, 2025 Maintainer Author

Uh oh!

Uh oh!

rasbtMar 2, 2025 Maintainer Author

Uh oh!

Uh oh!

rasbtMar 10, 2025 Maintainer Author

Uh oh!

Uh oh!

Alternative`gpt2` weight download#273

rasbt
Jul 19, 2024
Maintainer

Replies: 8 comments 7 replies

rasbt Dec 13, 2024
Maintainer Author

rasbt Mar 2, 2025
Maintainer Author

rasbt Mar 2, 2025
Maintainer Author

rasbt Mar 2, 2025
Maintainer Author

rasbt Mar 2, 2025
Maintainer Author

rasbt Mar 2, 2025
Maintainer Author

rasbt Mar 10, 2025
Maintainer Author