wql
|
2469598eb4
|
chore: add help.txt
|
2024-08-16 11:04:18 +00:00 |
|
wql
|
907282d2d7
|
add: inference result
|
2024-08-15 03:26:36 +00:00 |
|
wql
|
0e8b03b638
|
change: change predict yaml
|
2024-08-15 11:18:12 +08:00 |
|
wql
|
c97367ad0a
|
add: add predict yaml and chane old lora sft yaml
|
2024-08-15 11:05:49 +08:00 |
|
wql
|
1190dfe2f2
|
add: add results
|
2024-08-15 01:41:12 +00:00 |
|
wql
|
856bbeb6cc
|
add: add results folder
|
2024-08-14 18:02:04 +08:00 |
|
wql
|
cfb01ac39e
|
add: add flash-attn file
|
2024-08-14 16:31:14 +08:00 |
|
wql
|
faae9fa753
|
train: finish /train_24_8_13_13_16
|
2024-08-13 06:20:31 +00:00 |
|
wql
|
beb97a099c
|
train: change yaml
|
2024-08-13 13:19:42 +08:00 |
|
wql
|
6f7bca808a
|
train: add result of train_24_8_13_10_02/
|
2024-08-13 03:24:35 +00:00 |
|
wql
|
f44393f413
|
train: change yaml
|
2024-08-13 10:05:16 +08:00 |
|
wql
|
0841a0832f
|
train: change yaml
|
2024-08-13 09:10:03 +08:00 |
|
wql
|
2827dd1c98
|
train: finished /train_24_8_13_07_26/
|
2024-08-13 01:05:14 +00:00 |
|
wql
|
dc953dd514
|
train: change lr
|
2024-08-13 07:36:30 +08:00 |
|
wql
|
9fce0acb9b
|
train: finish train /train_24_8_12_23_21
|
2024-08-12 23:22:05 +00:00 |
|
wql
|
14451dd6f1
|
train: train_24_8_12_23_21
|
2024-08-12 23:27:42 +08:00 |
|
wql
|
4b0b73c570
|
train: train_24_8_12_23_21
|
2024-08-12 23:24:28 +08:00 |
|
wql
|
4e88b01cd1
|
change: change para
|
2024-08-12 18:05:29 +08:00 |
|
wql
|
65312954a1
|
change: change to en
|
2024-08-12 17:57:23 +08:00 |
|
wql
|
4b61aafe34
|
add:train_24_8_12_16_4
|
2024-08-12 09:44:49 +00:00 |
|
wql
|
4d5b12487f
|
fix: fix bug
|
2024-08-12 17:03:04 +08:00 |
|
wql
|
41c42f67a2
|
change: change llama2_lora_sft.yaml
|
2024-08-12 16:51:45 +08:00 |
|
wql
|
1ee249021b
|
add: add train_24_8_12_15_46
|
2024-08-12 08:13:14 +00:00 |
|
wql
|
01f70612c7
|
change: change llama2_lora_sft.yaml dataset to alpaca_zh
|
2024-08-12 15:47:08 +08:00 |
|
wql
|
90c6e4d020
|
fix: fix format
|
2024-08-12 15:42:18 +08:00 |
|
wql
|
d1718878af
|
fix: rerun jsonl_to_json.py
|
2024-08-12 07:39:07 +00:00 |
|
wql
|
a8fe8b98dc
|
update: update jsonl_to_json
|
2024-08-12 15:35:18 +08:00 |
|
wql
|
0da139a06b
|
add: add alpaca_zh.json
|
2024-08-12 07:26:30 +00:00 |
|
wql
|
9698ef9781
|
add: add jsonl to json py script
|
2024-08-12 15:23:43 +08:00 |
|
wql
|
ce742cdb8f
|
add: add jsonl file
|
2024-08-12 15:16:49 +08:00 |
|
wql
|
bbabfc674b
|
update saves
|
2024-08-12 06:39:25 +00:00 |
|
wql
|
533ad569eb
|
test: test commit
|
2024-08-12 14:34:56 +08:00 |
|
wql
|
5fb466926c
|
fix: remove saves from gitignore
|
2024-08-12 14:31:19 +08:00 |
|
wql
|
154eecf708
|
add: add llama2_lora_sft.yaml
|
2024-08-12 10:49:20 +08:00 |
|
hiyouga
|
c93d55bfb0
|
update readme
|
2024-08-10 10:17:35 +08:00 |
|
hiyouga
|
576a894f77
|
update readme
|
2024-08-09 20:46:02 +08:00 |
|
hiyouga
|
c75b5b83c4
|
add magpie ultra dataset
|
2024-08-09 20:28:55 +08:00 |
|
hiyouga
|
dc770efb14
|
add qwen2 math models
|
2024-08-09 20:20:35 +08:00 |
|
hiyouga
|
0a690ada6f
|
update examples
|
2024-08-09 20:13:46 +08:00 |
|
hiyouga
|
e2a28f51c6
|
add adam_mini to readme
|
2024-08-09 20:02:03 +08:00 |
|
hoshi-hiyouga
|
ef482394f0
|
Merge pull request #5095 from relic-yuexi/feat-optimizer
Feat optimizer
|
2024-08-09 19:51:33 +08:00 |
|
hiyouga
|
86f7099fa3
|
update scripts
|
2024-08-09 19:16:23 +08:00 |
|
hiyouga
|
c87023d539
|
follow #5115
|
2024-08-09 18:03:00 +08:00 |
|
hoshi-hiyouga
|
51542cb15f
|
Merge pull request #5115 from YeQiuO/main
fix: `Train on the last turn only` truncate bug
|
2024-08-09 17:58:27 +08:00 |
|
hoshi-hiyouga
|
984961c550
|
Merge pull request #5072 from relic-yuexi/main
fix the deepseekcoder template to avoid repeat problem
|
2024-08-09 16:35:21 +08:00 |
|
hoshi-hiyouga
|
4f62e1cb24
|
Update template.py
|
2024-08-09 16:27:42 +08:00 |
|
“Wzw”
|
2fa1e0b2ad
|
mask_history args verify valid
|
2024-08-08 10:12:01 +08:00 |
|
“Wzw”
|
b5ca86cc07
|
fix mask_history tiny bug
|
2024-08-08 10:09:33 +08:00 |
|
codingma
|
18e455c232
|
Merge pull request #5109 from codemayq/fix-example
fix eval_dataset in example
|
2024-08-07 18:30:05 +08:00 |
|
codingma
|
9a48f7e957
|
update wechat.jpg
|
2024-08-07 18:29:48 +08:00 |