Spaces:

Ruurd
/

lad

Running on Zero

App Files Files

lad / llama_diffusion_model.py

Commit History

Set to unidirectional for debugging

57e6bce
verified

Ruurd commited on Apr 14

Deal with float values

a721355
verified

Ruurd commited on Apr 14

Make attention mask float

8851563
verified

Ruurd commited on Apr 14

Update llama_diffusion_model.py

238c8f8
verified

Ruurd commited on Apr 14

Create safe fallback for models not yet initialized with masking_type

f2ca6a6
verified

Ruurd commited on Apr 14

Overhaul code for appropriate masking for full model instead of just attention layers

b43e862
verified

Ruurd commited on Apr 14

Fix attention_weights referenced before assigned bug

22370b2
verified

Ruurd commited on Apr 14

Implement improved attention masking for bidirectional_masked

1723639
verified

Ruurd commited on Apr 14

Change LoRA size from 256 to 512, also back to bidirectional_masked

620a6cd
verified

Ruurd commited on Apr 11

Changed back to bidirectional attention

e237f80
verified

Ruurd commited on Apr 11

Try out bidirectional_masked prediction

0daaccf

Ruurd commited on Apr 11

input_size?

a5ca1bf

Ruurd commited on Apr 8

input_size

f7efac8

Ruurd commited on Apr 8

Updated model architecture

0af2920

Ruurd commited on Apr 8

First commit

7252f98

Ruurd commited on Apr 8