1abdc99675
add server
2023-04-26 17:13:00 +08:00
3b18aa1cc6
fix bug and remove bnb
2023-04-20 09:51:57 +08:00
fb7665726e
Update requirements.txt
...
Pinned commit hash
2023-04-13 14:44:59 +08:00
5ff11b5bf2
Merge pull request #77 from winglian/upstream-peft
...
use monkey patch instead of forked peft
2023-04-13 10:25:05 +08:00
4261bd8070
add xformers support
2023-04-12 12:59:44 +08:00
c2b33bacc9
use monkey patch instead of forked peft
2023-04-09 11:40:58 -04:00
dba3773b30
add triton backend support for v2 model
2023-04-07 15:34:06 +08:00
9351f49542
merge pull request in new branch
2023-04-07 10:40:24 +08:00
30bf938d03
Update requirements.txt
2023-04-06 13:50:25 +02:00
f20570343f
GPTQv2 support
...
GPTQv2 support.
1. Adds dependency on `triton`
2. Refactors autograd_4bit to include both GPTQv1 and GPTQv2
3. Introduces new environment variable GPTQ_VERSION to select autograd_4bit version
4. Fixes triton kernels
5. Matrix multiplications are in fp16
2023-04-06 02:29:36 +03:00
b47da33084
fixes for most recent update
2023-03-28 10:56:35 -04:00
101d314bd9
add missing dependency to train with LlamaTokenizer
2023-03-27 16:13:46 -04:00
62e54ac1c7
backwards support for pre-py3.10, add datasets requirement used in train
2023-03-27 16:08:20 -04:00
96440c8717
Removing submodules actually.
2023-03-25 20:20:38 -07:00
dc036373b2
add more scripts and adjust code for transformer branch
2023-03-22 04:09:04 +00:00
551f62a0e8
add patch for gptq and peft
2023-03-18 13:31:48 +08:00
John Smith
Wing Lian
yamashi
Andrey Glushenkov
Star Dorminey