try the full model (no quantization)
91f531c
Running
henok3878
commited on
Spaces:
Running
Running
Commit History
remove priming
26ec32c
henok3878
commited on
support only single batch for now
f5121bb
henok3878
commited on
add updated model checkpoints
0f4a5c1
henok3878
commited on
refactor: change sampling to torch.inference_mode
99b28cc
henok3878
commited on
refactor: shorten style1 for better inference time on cpu
b302051
henok3878
commited on
fix: add style files and fix their path
b2d17dd
henok3878
commited on
refactor: update inference to use priming by default
a55bf24
henok3878
commited on
feature(utils): add utilities to support priming logic
70e1f1d
henok3878
commited on
feature: add style1 files (.txt and .npy)
a8bfa27
henok3878
commited on
refactor: add latest models with priming logic
f7f4fc6
henok3878
commited on
reafactor: increase valid bias range
fea5d40
henok3878
commited on
fix: update dockerfile to copy quantized model
32ee77c
henok3878
commited on
fix: remove invalid import
9b741f5
henok3878
commited on
feature: add quantized model for cpu inference
44bb151
henok3878
commited on
fix pytorch version in req.txt
56ecf7d
henok3878
commited on
add docker config
70e9cbc
henok3878
commited on
fix: fix REAME.md format
d3469ec
henok3878
commited on
configure git lfs to track model files
60eae0d
henok3878
commited on
initial commit
1599d2c
feat: init commit for hugging face space
a9beef1
henok3878
commited on