Closed eric-tc-wong closed 3 years ago
Thanks @eric-tc-wong for reporting this oversight!
Hi Tom,
Thank you for fixing this so quickly. I am glad to be of help.
Best, Eric
From: Tom Sercu @.> Sent: Monday, July 12, 2021 9:35 PM To: facebookresearch/esm @.> Cc: eric-tc-wong @.>; Mention @.> Subject: Re: [facebookresearch/esm] load_model_and_alphabet_local model_name not defined (#101)
Thanks @eric-tc-wonghttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Feric-tc-wong&data=04%7C01%7C%7C76d7aaf73cc44c2dc6e408d9459e6008%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C637617368779824346%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=YeZ4y%2BMch1U%2BldCNKRUNMAkL2l10n4XqqT5KBP7BHYA%3D&reserved=0 for reporting this oversight!
- You are receiving this because you were mentioned. Reply to this email directly, view it on GitHubhttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Ffacebookresearch%2Fesm%2Fissues%2F101%23issuecomment-878708550&data=04%7C01%7C%7C76d7aaf73cc44c2dc6e408d9459e6008%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C637617368779824346%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=mP65bN7of95ZtyG5uGyNAKeeTN6KtZ2UE6Uezn5Nnug%3D&reserved=0, or unsubscribehttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnotifications%2Funsubscribe-auth%2FAUJE3H6QEWFCP6JOKZXPIO3TXOJ2ZANCNFSM5AHQLLRA&data=04%7C01%7C%7C76d7aaf73cc44c2dc6e408d9459e6008%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C637617368779834292%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=mrZoP3sqpt%2BqzJn%2F8hbk0QXuak4cXONe8b5YJcN2T68%3D&reserved=0.
Hello,
Thank you for making these wonderful models available, and congratulations on the new publication. The new update broke the code for loading local models.
Bug description
At load_model_and_alphabet_local, "model_name" is not defined.
Reproduction steps
model_dir = prepend_dir + './esm1b_t33_650M_UR50S.pt' model, alphabet = esm.pretrained.load_model_and_alphabet_local(model_dir)
Logs