Commits · omer11a/bounded-attention

Revert back to previous sdk version

7e8085c

Running

omer11a commited on Apr 20

Fixed some stuff

97abb9e

omer11a commited on Apr 20

Move token index entry to advanced options (#1)

0ea3f87
verified

omer11a

multimodalart HF staff commited on Apr 20

Fixed typo

8f5c850

omer11a commited on Apr 19

Improved user interface

14451ef

omer11a commited on Apr 18

Added placeholders

4159aad

omer11a commited on Apr 12

Added first_refinement_step to examples

3d7f2bc

omer11a commited on Apr 11

Improved examples

b55c5db

omer11a commited on Apr 11

Added a new line

4a4e11d

omer11a commited on Apr 11

Improved examples

3894e3f

omer11a commited on Apr 11

Added another example

58ad0e0

omer11a commited on Apr 10

Used diffusers==0.20.0

77e9eec

omer11a commited on Apr 10

Modified examples

72df8c8

omer11a commited on Apr 10

Decreased duration

9d8ec57

omer11a commited on Apr 7

Increased optimization steps

80df329

omer11a commited on Apr 7

Faster loading

61862e4

omer11a commited on Apr 4

Fixed errors

333e56c

omer11a commited on Apr 4

Fixed errors

134ec95

omer11a commited on Apr 4

Download model locally

dfc5415

omer11a commited on Apr 4

Load float32 model

d157117

omer11a commited on Apr 3

Fixed errors

431d204

omer11a commited on Apr 3

Updated diffusers code

c89d950

omer11a commited on Apr 3

Load model to CPU

86a22a6

omer11a commited on Apr 3

Updated requirements.txt

bdfcbd1

omer11a commited on Apr 3

Decreased running time

caa1c82

omer11a commited on Apr 3

Fixed errors

4ca09f6

omer11a commited on Apr 3

Load model directly to GPU

78b6f81

omer11a commited on Apr 3

Fixed errors

1e9f321

omer11a commited on Apr 3

Fixed errors

cc776b8

omer11a commited on Apr 3

Fixed errors

f42e996

omer11a commited on Apr 3

Decreased runtime

49a7542

omer11a commited on Apr 3

Fixed bug in input parsing

f0d244c

omer11a commited on Apr 2

Removed examples

5368ac9

omer11a commited on Apr 2

Fix examples

b322d0b

omer11a commited on Apr 1

Added duplicate space link

4c60292

omer11a commited on Apr 1

Added examples

0b407fa

omer11a commited on Apr 1

Improved memory efficiency

8fea73b

omer11a commited on Apr 1

Decreased duration

39ce2cf

omer11a commited on Mar 29

Increased duration

5ebee8d

omer11a commited on Mar 29

Improved memory requirements

056b358

omer11a commited on Mar 29

Improved memory efficiency

1127ecd

omer11a commited on Mar 28

Fixed error

3342cb9

omer11a commited on Mar 27

Remove prints

154600e

omer11a commited on Mar 27

Creates model inside GPU

e7e4657

omer11a commited on Mar 27

Move model to GPU only inside generate function

4b19f84

omer11a commited on Mar 27

Allow repeated inference

137c79d

omer11a commited on Mar 27

Use full precision

fa4d90e

omer11a commited on Mar 27

Use full precision

33651e9

omer11a commited on Mar 27

Fixed bug

e8c5d53

omer11a commited on Mar 27

Removed queue

2aebc5f

omer11a commited on Mar 27

Commit History

Revert back to previous sdk version 7e8085c Running

Fixed some stuff 97abb9e

Move token index entry to advanced options (#1) 0ea3f87 verified

Fixed typo 8f5c850

Improved user interface 14451ef

Added placeholders 4159aad

Added first_refinement_step to examples 3d7f2bc

Improved examples b55c5db

Added a new line 4a4e11d

Improved examples 3894e3f

Added another example 58ad0e0

Used diffusers==0.20.0 77e9eec

Modified examples 72df8c8

Decreased duration 9d8ec57

Increased optimization steps 80df329

Faster loading 61862e4

Fixed errors 333e56c

Fixed errors 134ec95

Download model locally dfc5415

Load float32 model d157117

Fixed errors 431d204

Updated diffusers code c89d950

Load model to CPU 86a22a6

Updated requirements.txt bdfcbd1

Decreased running time caa1c82

Fixed errors 4ca09f6

Load model directly to GPU 78b6f81

Fixed errors 1e9f321

Fixed errors cc776b8

Fixed errors f42e996

Decreased runtime 49a7542

Fixed bug in input parsing f0d244c

Removed examples 5368ac9

Fix examples b322d0b

Added duplicate space link 4c60292

Added examples 0b407fa

Improved memory efficiency 8fea73b

Decreased duration 39ce2cf

Increased duration 5ebee8d

Improved memory requirements 056b358

Improved memory efficiency 1127ecd

Fixed error 3342cb9

Remove prints 154600e

Creates model inside GPU e7e4657

Move model to GPU only inside generate function 4b19f84

Allow repeated inference 137c79d

Use full precision fa4d90e

Use full precision 33651e9

Fixed bug e8c5d53

Removed queue 2aebc5f

Revert back to previous sdk version

7e8085c

Running

Fixed some stuff

97abb9e

Move token index entry to advanced options (#1)

0ea3f87
verified

Fixed typo

8f5c850

Improved user interface

14451ef

Added placeholders

4159aad

Added first_refinement_step to examples

3d7f2bc

Improved examples

b55c5db

Added a new line

4a4e11d

Improved examples

3894e3f

Added another example

58ad0e0

Used diffusers==0.20.0

77e9eec

Modified examples

72df8c8

Decreased duration

9d8ec57

Increased optimization steps

80df329

Faster loading

61862e4

Fixed errors

333e56c

Fixed errors

134ec95

Download model locally

dfc5415

Load float32 model

d157117

Fixed errors

431d204

Updated diffusers code

c89d950

Load model to CPU

86a22a6

Updated requirements.txt

bdfcbd1

Decreased running time

caa1c82

Fixed errors

4ca09f6

Load model directly to GPU

78b6f81

Fixed errors

1e9f321

Fixed errors

cc776b8

Fixed errors

f42e996

Decreased runtime

49a7542

Fixed bug in input parsing

f0d244c

Removed examples

5368ac9

Fix examples

b322d0b

Added duplicate space link

4c60292

Added examples

0b407fa

Improved memory efficiency

8fea73b

Decreased duration

39ce2cf

Increased duration

5ebee8d

Improved memory requirements

056b358

Improved memory efficiency

1127ecd

Fixed error

3342cb9

Remove prints

154600e

Creates model inside GPU

e7e4657

Move model to GPU only inside generate function

4b19f84

Allow repeated inference

137c79d

Use full precision

fa4d90e

Use full precision

33651e9

Fixed bug

e8c5d53

Removed queue

2aebc5f