Commit graph

426 commits

Author SHA1 Message Date
Daniel Han-Chen
aa032fc80d Update mistral.py 2024-02-04 01:46:04 +11:00
Daniel Han-Chen
31578f2010 fast inference 2024-02-04 01:42:46 +11:00
Daniel Han-Chen
257cd7d531 Update llama.py 2024-02-03 23:22:21 +11:00
Daniel Han-Chen
e500b785f7 Update llama.py 2024-02-03 23:12:16 +11:00
Daniel Han-Chen
cf0fae9a55 Update llama.py 2024-02-03 23:01:56 +11:00
Daniel Han-Chen
381b991c45 Update llama.py 2024-02-03 22:42:11 +11:00
Daniel Han-Chen
665908eb70 Update llama.py 2024-02-03 22:28:20 +11:00
Daniel Han-Chen
5534f8a8f1 more temp matrices 2024-02-03 20:22:42 +11:00
Daniel Han-Chen
68db1c7af7 fast inference again 2024-02-03 19:44:36 +11:00
Daniel Han-Chen
d76f583349 Update mistral.py 2024-02-03 19:30:22 +11:00
Daniel Han-Chen
9225dd6708 Update llama.py 2024-02-03 19:19:13 +11:00
Daniel Han-Chen
8270821269 Update llama.py 2024-02-03 19:08:42 +11:00
Daniel Han-Chen
1c6e1f18b4 Update llama.py 2024-02-03 18:32:18 +11:00
Daniel Han-Chen
dd03abedd6 Update llama.py 2024-02-03 18:20:06 +11:00
Daniel Han-Chen
522f6dbfd2 Update llama.py 2024-02-03 18:07:55 +11:00
Daniel Han-Chen
ad357dec89 fast inference + saving config.json 2024-02-03 03:52:25 +11:00
Daniel Han-Chen
a78d6fba7e Update llama.py 2024-02-03 03:34:02 +11:00
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