BlinkDL
|
a268cd2e40
|
better tinyAtt
|
3 years ago |
BlinkDL
|
e9b24370d9
|
RWKV-4a (tinyAtt)
|
3 years ago |
BlinkDL
|
2567c8c904
|
rescale to avoid FP16 overflow
|
3 years ago |
BlinkDL
|
aef9f6f7ef
|
fp16
|
3 years ago |
BlinkDL
|
8a4a41a3aa
|
better
|
3 years ago |
BlinkDL
|
daed379db2
|
bf16 inference - 15G VRAM for 7b model
|
3 years ago |
BlinkDL
|
1479315677
|
update
|
3 years ago |
BlinkDL
|
40237495cc
|
bugfix
|
3 years ago |
BlinkDL
|
c7155525bb
|
better
|
3 years ago |
BlinkDL
|
fc3bc1eb0e
|
good for UTF-8 inference (such as CJK)
|
3 years ago |
BlinkDL
|
77bcaa8247
|
+AE model
|
3 years ago |
BlinkDL
|
9e325b88cb
|
OpenCLIP
|
3 years ago |
BlinkDL
|
74fedc0d86
|
CLIP-guided Binary AutoEncoder
|
3 years ago |
BlinkDL
|
bb59fffac1
|
img model
|
3 years ago |
BlinkDL
|
40e91dd1d7
|
img models (wip)
|
3 years ago |
BlinkDL
|
3a7e6a6aa3
|
faster inference
|
3 years ago |
BlinkDL
|
44f07e44d2
|
better
|
3 years ago |
BlinkDL
|
74ffd9bec7
|
multinode
|
3 years ago |
BlinkDL
|
470ac7d1fa
|
better
|
3 years ago |
BlinkDL
|
24e3cf6e93
|
better
|
3 years ago |
BlinkDL
|
1189c9e238
|
fix
|
3 years ago |
BlinkDL
|
7b92a979d8
|
fix
|
3 years ago |
BlinkDL
|
ceafd4e7af
|
better
|
3 years ago |
BlinkDL
|
94300caba1
|
better
|
3 years ago |
BlinkDL
|
99a3dff414
|
code for pile training
|
3 years ago |
BlinkDL
|
d1674732ed
|
clean code
|
3 years ago |
BlinkDL
|
2388bca7c3
|
dummy data example
|
3 years ago |
BlinkDL
|
778c0a7f58
|
improvements
|
3 years ago |
BlinkDL
|
f81349f127
|
fix
|
3 years ago |
BlinkDL
|
6ab2e71c25
|
finetuning 1.5B model using 16G VRAM
|
3 years ago |
BlinkDL
|
23b0c74950
|
fix
|
3 years ago |
BlinkDL
|
cdb098c0e0
|
fix
|
3 years ago |
BlinkDL
|
8abea9c08d
|
wip
|
3 years ago |
BlinkDL
|
ba6e9e6264
|
rwkv-v4neo test
|
3 years ago |