This website requires JavaScript.
Explore
Help
Register
Sign In
mrq
/
vall-e
Watch
5
Star
9
Fork
0
You've already forked vall-e
Code
Issues
8
Pull Requests
Packages
Projects
Releases
Wiki
Activity
2ea387c08a
vall-e
/
vall_e
/
models
History
mrq
2ea387c08a
segregated experimental changes into its own streamlined file to avoid breaking the existing model, and it can pivot to the cleaned up code if it actually works (nothing is working)
2025-02-26 21:26:13 -06:00
..
arch
added muon optimizer through kludge hacks because it necessitates a second optimizer in tandum that seems to only sometimes work with deepspeed
2025-02-23 11:22:13 -06:00
__init__.py
segregated experimental changes into its own streamlined file to avoid breaking the existing model, and it can pivot to the cleaned up code if it actually works (nothing is working)
2025-02-26 21:26:13 -06:00
ar_nar_v2.py
segregated experimental changes into its own streamlined file to avoid breaking the existing model, and it can pivot to the cleaned up code if it actually works (nothing is working)
2025-02-26 21:26:13 -06:00
ar_nar.py
segregated experimental changes into its own streamlined file to avoid breaking the existing model, and it can pivot to the cleaned up code if it actually works (nothing is working)
2025-02-26 21:26:13 -06:00
base_v2.py
segregated experimental changes into its own streamlined file to avoid breaking the existing model, and it can pivot to the cleaned up code if it actually works (nothing is working)
2025-02-26 21:26:13 -06:00
base.py
segregated experimental changes into its own streamlined file to avoid breaking the existing model, and it can pivot to the cleaned up code if it actually works (nothing is working)
2025-02-26 21:26:13 -06:00
lora.py
naive model offloading support (handles automatically splitting parts of the model to requested device per memory constraints, either inferred or requested in the yaml, input tensors are automatically migrated to the right device, it SEEMS to work for training under the test trainer when split between GPU and CPU) (this was specifically only because that Flux imagegen model released so I can test it there)
2024-08-01 20:12:06 -05:00