John Smith
|
cd1a299ba3
|
Merge pull request #18 from s4rduk4r/finetune-refactor
Refactor finetune.py
|
2023-03-25 10:29:36 +08:00 |
|
John Smith
|
0879580006
|
Merge branch 'main' into finetune-refactor
|
2023-03-25 10:29:02 +08:00 |
|
John Smith
|
e64bd6a214
|
Create LICENSE
|
2023-03-25 10:17:44 +08:00 |
Andrey Glushenkov
|
397f5041c3
|
Reflect last changes in main
Reflect commits:
4906961bf1
60b227d0ba
|
2023-03-24 15:46:03 +03:00 |
|
Andrey Glushenkov
|
50dbb101e9
|
Refactor finetune.py
1. Add command line arguments support
2. Add Stanford Alpaca-like dataset support. Used code from - https://github.com/tloen/alpaca-lora
3. Fix LoRA pre-train application
|
2023-03-24 14:15:07 +03:00 |
|
John Smith
|
4906961bf1
|
fix bug
|
2023-03-23 23:37:39 +08:00 |
|
John Smith
|
94851cec68
|
Merge pull request #14 from Ph0rk0z/AtomicAddHalf
Fix cuda kernel for Pascal & Cuda 6/6.1
|
2023-03-23 20:40:29 +08:00 |
Forkoz
|
58998acc9f
|
Fix cuda kernel for Pascal & Cuda 6/6.1
When I left the other functions to use normal atomic add it seemed like a small speedup. 4.79 it/s vs 5.23 it/s
|
2023-03-23 07:33:57 -05:00 |
|
John Smith
|
60b227d0ba
|
fix minor bug
|
2023-03-23 08:43:18 +00:00 |
|
John Smith
|
619a177fbb
|
Update README.md
|
2023-03-23 16:31:49 +08:00 |
|
John Smith
|
44978669cf
|
Add gradient checkpointing
|
2023-03-23 08:25:29 +00:00 |
|
John Smith
|
eb8ce878d4
|
Merge pull request #6 from sterlind/patch-1
Fix path to autograd_4bit.py in install.sh
|
2023-03-22 16:07:25 +08:00 |
|
John Smith
|
9b04b8eec6
|
add monkey patch for webui
|
2023-03-22 07:58:51 +00:00 |
sterlind
|
0aea8f45e3
|
Fix path to autograd_4bit.py in install.sh
|
2023-03-22 00:24:52 -07:00 |
|
John Smith
|
45d2f22c14
|
Update README.md
|
2023-03-22 14:56:50 +08:00 |
|
John Smith
|
cab067fef9
|
Update README.md
|
2023-03-22 14:55:24 +08:00 |
|
John Smith
|
02bd0338f1
|
add data
|
2023-03-22 12:13:34 +08:00 |
|
John Smith
|
dc036373b2
|
add more scripts and adjust code for transformer branch
|
2023-03-22 04:09:04 +00:00 |
|
John Smith
|
a955a1c2a5
|
fix bug
|
2023-03-22 00:18:24 +08:00 |
|
John Smith
|
467849d13a
|
Merge branch 'main' of https://github.com/johnsmith0031/alpaca_lora_4bit
|
2023-03-21 09:45:06 +00:00 |
|
John Smith
|
ef0a326cec
|
update autograd
|
2023-03-21 09:41:18 +00:00 |
|
John Smith
|
3be75bb3db
|
Update README.md
|
2023-03-21 16:49:08 +08:00 |
|
John Smith
|
8d198e0171
|
Update README.md
|
2023-03-21 16:48:17 +08:00 |
|
John Smith
|
3471be4e56
|
add fast_4bit_matmul and auto switch 2 methods according to bottleneck
|
2023-03-21 08:43:07 +00:00 |
|
John Smith
|
dd0d5a31f7
|
add half support
|
2023-03-20 09:37:51 +00:00 |
|
John Smith
|
5b64833390
|
add half support on cuda kernel
|
2023-03-20 09:19:05 +00:00 |
|
John Smith
|
5c1411ff18
|
Update README.md
|
2023-03-20 15:04:18 +08:00 |
|
John Smith
|
04f5575a23
|
reduced memory usage by a little
|
2023-03-20 00:51:52 +08:00 |
|
John Smith
|
2b84b32fbe
|
Update autograd_4bit.py
|
2023-03-18 22:13:11 +08:00 |
|
John Smith
|
6f4bbb40a9
|
Update autograd_4bit.py
|
2023-03-18 18:49:26 +08:00 |
|
John Smith
|
fecce0e1a5
|
Update README.md
|
2023-03-18 18:21:01 +08:00 |
|
John Smith
|
ae04f88e57
|
Update README.md
|
2023-03-18 13:36:06 +08:00 |
|
John Smith
|
bbaf1b1bf5
|
Update README.md
|
2023-03-18 13:35:36 +08:00 |
|
John Smith
|
551f62a0e8
|
add patch for gptq and peft
|
2023-03-18 13:31:48 +08:00 |
|
John Smith
|
326bc9214a
|
Update README.md
|
2023-03-18 13:26:04 +08:00 |
|
John Smith
|
42118e3267
|
Initial commit
|
2023-03-18 13:21:20 +08:00 |