Commit graph

409 commits

Author SHA1 Message Date
Daniel Han-Chen
fa3d23406e Update utils.py 2024-02-03 03:10:39 +11:00
Daniel Han-Chen
8e3f0296be Update utils.py 2024-02-03 02:55:22 +11:00
Daniel Han-Chen
404e177adb Update utils.py 2024-02-03 02:30:47 +11:00
Daniel Han-Chen
a81d193830 Update utils.py 2024-02-03 02:20:00 +11:00
Daniel Han-Chen
4436a1099d Update llama.py 2024-02-03 01:50:48 +11:00
Daniel Han-Chen
a15ffc95e0 Update llama.py 2024-02-03 01:48:03 +11:00
Daniel Han-Chen
0be46406d8 Update llama.py 2024-02-03 01:39:39 +11:00
Daniel Han-Chen
e911047188 Update llama.py 2024-02-03 01:35:45 +11:00
Daniel Han-Chen
c934c16e21 Update llama.py 2024-02-03 01:29:50 +11:00
Daniel Han-Chen
705bbba5c5 Update llama.py 2024-02-03 01:22:53 +11:00
Daniel Han-Chen
9c2bed35b9 Update llama.py 2024-02-02 23:45:02 +11:00
Daniel Han-Chen
ea9b4eea0c Update llama.py 2024-02-02 23:40:52 +11:00
Daniel Han-Chen
c6ad936f88 Update llama.py 2024-02-02 23:32:58 +11:00
Daniel Han-Chen
03df291110 Update llama.py 2024-02-02 23:32:36 +11:00
Daniel Han-Chen
dc2740416b Update llama.py 2024-02-02 22:26:47 +11:00
Daniel Han-Chen
b33c92d1bd Update llama.py 2024-02-02 22:22:42 +11:00
Daniel Han-Chen
923c6bad14 Update llama.py 2024-02-02 22:20:45 +11:00
Daniel Han-Chen
b3703926ca Update llama.py 2024-02-02 22:17:02 +11:00
Daniel Han-Chen
1b274212e1 Update llama.py 2024-02-02 20:35:00 +11:00
Daniel Han-Chen
9df19aeb9f past_key_values 2024-02-02 20:32:21 +11:00
Daniel Han-Chen
82eea75cde torch compile 2024-02-02 20:29:35 +11:00
Daniel Han-Chen
e748078095 Update llama.py 2024-02-02 20:24:44 +11:00
Daniel Han-Chen
9146fa443d Update llama.py 2024-02-02 20:24:28 +11:00
Daniel Han-Chen
a5a123db08 Update llama.py 2024-02-02 20:20:14 +11:00
Daniel Han-Chen
82ead808d5 Update llama.py 2024-02-02 20:19:15 +11:00
Daniel Han-Chen
1497521e5c Update mistral.py 2024-02-02 20:06:52 +11:00
Daniel Han-Chen
c3c454a729 Update llama.py 2024-02-02 20:06:31 +11:00
Daniel Han-Chen
f299c9cde1 Update llama.py 2024-02-02 19:44:52 +11:00
Daniel Han-Chen
0e1d67d4e1 fast inference 2024-02-02 19:07:41 +11:00
Daniel Han-Chen
168ded977e Update llama.py 2024-02-02 18:28:05 +11:00
Daniel Han-Chen
bf441055ca faster inference 2024-02-02 18:14:31 +11:00
Daniel Han-Chen
7c2b04254c Update llama.py 2024-02-02 16:59:02 +11:00
Daniel Han-Chen
ca99d7c194 Update mistral.py 2024-02-02 16:46:30 +11:00
Daniel Han-Chen
40e8848c4e Update llama.py 2024-02-02 15:56:56 +11:00
Daniel Han-Chen
6cc9835021 Update llama.py 2024-02-02 13:52:12 +11:00
Daniel Han-Chen
7ad1a1fa62 Update llama.py 2024-02-02 04:18:34 +11:00
Daniel Han-Chen
0b661a23b9 Update llama.py 2024-02-02 03:55:36 +11:00
Daniel Han-Chen
da64d3403c Update llama.py 2024-02-01 23:54:01 +11:00
Daniel Han-Chen
abc47836dc Update llama.py 2024-02-01 23:41:32 +11:00
Daniel Han-Chen
f231c4f395 Update llama.py 2024-02-01 23:41:23 +11:00
Daniel Han-Chen
5f3c51b394 Update llama.py 2024-02-01 23:41:11 +11:00
Daniel Han-Chen
e0ea238256 Update llama.py 2024-02-01 23:40:36 +11:00
Daniel Han-Chen
73f63d6884 Update llama.py 2024-02-01 23:38:07 +11:00
Daniel Han-Chen
e4b5e38800 inference 2024-02-01 23:17:53 +11:00
Daniel Han-Chen
334c5ed1f0 Update llama.py 2024-02-01 22:48:54 +11:00
Daniel Han-Chen
cd39f6108f lm_head 2024-02-01 22:34:33 +11:00
Daniel Han-Chen
24c4c37b7c revert 2024-02-01 22:21:35 +11:00
Daniel Han-Chen
e791db9b06 Update llama.py 2024-02-01 20:12:59 +11:00
Daniel Han-Chen
1793a16c8f faster inference 2024-02-01 20:03:54 +11:00
Daniel Han-Chen
19fb50e244 Update utils.py 2024-02-01 19:56:54 +11:00