wql
|
e6e5cd97e1
|
chore: change lr to original
|
2024-10-23 16:06:02 +08:00 |
|
wql
|
b00575852e
|
del: del results
|
2024-10-12 10:57:02 +08:00 |
|
wql
|
1ac91733e4
|
feat: add include_num_input_tokens_seen
|
2024-09-26 14:46:39 +08:00 |
|
wql
|
cc8d2e7ea0
|
chore: change lr
|
2024-09-26 11:10:31 +08:00 |
|
wql
|
4d27d046a0
|
chore: change lr
|
2024-09-19 17:08:17 +08:00 |
|
wql
|
735b989587
|
chore: change lr
|
2024-09-19 16:05:33 +08:00 |
|
wql
|
5a306611bc
|
train: qwen
|
2024-09-19 15:11:35 +08:00 |
|
wql
|
bbbe4e2d00
|
testrun: test inference
|
2024-09-19 13:30:51 +08:00 |
|
wql
|
63556d6571
|
testrun: single card
|
2024-09-18 16:33:23 +08:00 |
|
wql
|
8d6f544698
|
testrun: test 910b qwen
|
2024-09-18 15:55:06 +08:00 |
|
wql
|
934a5993ac
|
add: add baichuan inference results
|
2024-09-13 08:19:38 +00:00 |
|
wql
|
f15e37dfad
|
fix: fix bf16
|
2024-09-05 15:49:32 +08:00 |
|
wql
|
62a486dfc0
|
add: add test file
|
2024-09-05 07:07:49 +00:00 |
|
wql
|
c6a4d43c06
|
fix: remove no need test file
|
2024-09-05 07:05:47 +00:00 |
|
wql
|
ab4bf8bd4d
|
add: add all test results
|
2024-09-05 06:52:33 +00:00 |
|
wql
|
fa9a9007f9
|
chore: add lora sft and predict template yaml file
|
2024-09-04 16:52:15 +08:00 |