Mrigank Tiwari
Mrigank Tiwari
No, I have Ubuntu 20.
> Yes. I have an issue with colab. But I don't have an issue with the local VScode Jupyter notebook. The local Jupyter notebook version is **Python 3.7.13** The tested...
Has anyone found a solution yet? I tried with 'gpt2-large' as well. And it just bumps into same error: ```File "/home/test/miniconda3/envs/qags/lib/python3.6/site-packages/transformers/tokenization_utils_base.py", line 3113, in decode **kwargs, File "/home/test/miniconda3/envs/qags/lib/python3.6/site-packages/transformers/tokenization_utils.py", line 729,...
> Thanks for your contribution and works. > > May I ask you what is ''wget https://bapengstorage.blob.core.windows.net/fileshare/scgpt.tar.gz''? > > what dataset were used for this pre-trained scgpt model? > >...
From the response in below link it appears the available pre-trained model is not fine-tuned on MULTIWOZ, so must be on DSTC and facebook data (I don't know which one...
Also when I use the HF model with replaced BitLinear layers, the generations isn't working. - The ```.generate``` with Llama2 model, completes generation in ~68 seconds - Whereas, doing same...
> I think it's [here](https://drive.google.com/drive/folders/1GP75Jp1XuPnfidhMtc1ey_-zjFKDxUoh?usp=sharing). Yeah, this is correct.
Has anyone here found a way to generate the "test.src" file in generate questions section?
I never found the solution, and long back moved away from trying as well. If someone finds the solution please provide here.
Am facing the same issue, appreciate any help.