Brett Kuprel
|
e4c2be54cb
|
save converted detokenizer params
|
2022-07-01 10:17:29 -04:00 |
|
Brett Kuprel
|
df9aa6f915
|
sort -> topk, prev_token_and_index -> prev_token, token_index
|
2022-06-30 09:04:11 -04:00 |
|
Brett Kuprel
|
fb97ba5e20
|
update readme, cleanup
|
2022-06-30 07:41:31 -04:00 |
|
Brett Kuprel
|
d99828a239
|
simplified flax attention and matched torch attention
|
2022-06-29 14:56:28 -04:00 |
|
Brett Kuprel
|
661ec976ac
|
simplified attention for torch model
|
2022-06-29 13:48:12 -04:00 |
|
Brett Kuprel
|
ed91ab4a30
|
refactored to load models once and run multiple times
|
2022-06-29 09:42:12 -04:00 |
|
Brett Kuprel
|
17c96fe110
|
works with cuda
|
2022-06-28 21:28:36 -04:00 |
|
Brett Kuprel
|
9d6b6dcc92
|
previous commit broke flax model, fixed now
|
2022-06-28 12:54:58 -04:00 |
|
Brett Kuprel
|
5aa6fe49bf
|
use cuda if available
|
2022-06-28 12:47:11 -04:00 |
|
Brett Kuprel
|
aef24ea157
|
torch.no_grad(), cleanup
|
2022-06-28 12:16:44 -04:00 |
|
Brett Kuprel
|
c936d26102
|
back to linear attention
|
2022-06-27 13:19:03 -04:00 |
|
Brett Kuprel
|
018414a5c3
|
fixed relative imports
|
2022-06-27 12:43:47 -04:00 |
|