Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Split STATE from OM #66

Open
9 of 15 tasks
rburghol opened this issue Jun 22, 2023 · 0 comments
Open
9 of 15 tasks

Split STATE from OM #66

rburghol opened this issue Jun 22, 2023 · 0 comments

Comments

@rburghol
Copy link

rburghol commented Jun 22, 2023 •
edited
Loading

  • Create state.py with state dict code only
  • Create state branch
    • Load all Dicts in main.py
    • Split out op_tokens and model_object_cache and put in om
    • Pass Dicts into HYDR
    • Allow structure so that state Dict can hold all module Dicts like om
    • Create dynamic loader
    • Demo dynamic loader with code
    • Do PR
  • Create om branch (should inherit state branch)
    • Make sure that op_tokens is set early in process, should it be part of default state setup, or established in OM?
      • Same, where to set up model_object_cache
    • Load any local .json files
    • add step to call model_path_loader() after model_object_cache is set up
    • call model_tokenizer_recursive to finalize the token process and be ready for loading.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@rburghol