Closed GemmaTuron closed 7 months ago
Hi @GemmaTuron, love the work you're doing with @ersilia-os! Thank you for reporting this issue. I believe it boils down to the same issue as #84. I'm looking into it!
@GemmaTuron was this issue fixed by #84 ?
Hi @maclandrol !
Sorry for not answering before, yes, this is solved by #84 ! I'll close this issue
Is there an existing issue for this?
Bug description
Hi!
I am using molfeat in a conda env (I've tried Python 3.8 and 3.10) by running
pip install molfeat=0.9.4
. When I try to fetch a model, for example ChemGPT4.7M, I get the following error message:molfeat.store.modelstore.ModelStoreError: Can't retrieve model ChemGPT4.7M from the store !
I've also tried other Pretrained HF transformers like ChemGPT-19M and GPT2-Zinc480 with the same result. It seems related to where the models are stored locally (see below) but I am unable to bypass it. Any help will be greatly appreciated!
How to reproduce the bug
Error messages and logs
Environment
Current environment
``` #- Molfeat version (e.g., 0.1.0): 0.9.4 #- PyTorch Version (e.g., 1.10.0): #- RDKit version (e.g., 2022.09.5): 2023.9.1 #- scikit-learn version (e.g., 1.2.1): 1.3.2 #- OS (e.g., Linux): Ubuntu 22.04.3 LTS (Jammy Jellyfish) #- How you installed Molfeat (`conda`, `pip`, source): pip ```Additional context
No response