Post
824
What’s your biggest headache deploying Hugging Face models to the cloud—and how can we fix it for you?
Join the conversation
Join the community of Machine Learners and AI enthusiasts.
Sign Up
probably a good thing there aren't many responses here, yes?
When I push a model that has multiple shards to a repo that originally had less or more shards, it fetches all of them, even if they're a different architecture (ie pushing a 3-shard model to what was a 1-shard model only fetches the 1-shard model, instead of overwriting it)
push to hub 1-shard model
push to hub 3-shard model
fetch from hub - only fetches model.safetensors, not model-00001-of-00003.safetensors through model-00003-of-00003.safetensors
probably wasn't fixed because it's not very common to use the same repo for different architectures like i do
What about letting the user supply a pipeline.py in the repository that the loader will automatically parse and use? For if you have a custom architecture or something.