69 Commits

Author SHA1 Message Date
hiyouga
b92214f78b fix #4699
slow tokenizer for yi models


Former-commit-id: 4d23a0bcda0c15a903a62eec72d14c584ce020dd
2024-07-14 15:34:22 +08:00
hiyouga
3d219b91b9 fix packing for eager/sdpa attn
Former-commit-id: 735a033ceb7f2da6da71d138ea091d8a665411a9
2024-07-04 01:52:43 +08:00
hiyouga
60558388ec update packing
Former-commit-id: f3d9c31efa0e64317bdd5b4ed6f78653cf3b5ba4
2024-07-04 01:10:55 +08:00
hiyouga
5acaa476d6 update hparams
Former-commit-id: 1c4feac44192b1f540208837f5a530b0d3f5fb37
2024-07-03 23:18:58 +08:00
ancv
20fdf177e8 move efficient_packing from data_args to model_args
Former-commit-id: 7b61659c707480bcf8c802c73e10d12ad5b9b965
2024-07-02 18:37:55 +07:00
hoshi-hiyouga
a715490c2a Merge branch 'main' into main
Former-commit-id: 7be442f37d53a0c6324728fa1fa8e2c84d7f0fa5
2024-07-01 21:01:09 +08:00
hiyouga
67d2eb6b2a fix #4402 #4617
Deprecate reserved_label_len arg


Former-commit-id: 4b6568984c0be4b31e7aa91b7c0d52b7f7b12b0b
2024-07-01 01:19:27 +08:00
hiyouga
cfdf5a5a78 increase pissa_iter for stability
Former-commit-id: 03f8d9b0fb10ae58e7f68508197330d616957899
2024-06-28 03:18:54 +08:00
hiyouga
46f0189e88 refactor pissa, improve llamaboard
Former-commit-id: 619556e46c19718f702c97df5d570a2a4c5fb13a
2024-06-28 01:04:24 +08:00
hiyouga
9103fdf866 fix #4549
Former-commit-id: c9fdef10de737d1f433209812ef73e29cb60490a
2024-06-28 00:41:58 +08:00
hiyouga
bf99223a80 tiny fix
Former-commit-id: c1a78a3a9f8ab9d57577cee37f9c457d60863ba2
2024-06-27 20:14:48 +08:00
hiyouga
8aaf1185a5 support HQQ/EETQ #4113
Former-commit-id: b7cb51ddb394f04fe4646b2c297fc8d918c9979e
2024-06-27 00:29:42 +08:00
hiyouga
98f382fda3 lint
Former-commit-id: c9e424d2198b5872ce118a6ab4c109bf73be2bee
2024-06-25 02:55:50 +08:00
hiyouga
9fd7a410bb tiny fix about badam
Former-commit-id: 03f49267c7406e36aee35639f86e6e0383897090
2024-06-25 01:54:53 +08:00
hoshi-hiyouga
bfb2ad7c79 Merge pull request #4352 from Ledzy/main
[Enhancement] Support ZeRO-3 when using BAdam

Former-commit-id: 0dc75275efa7d7540b472783a52ea6aeaa503c0b
2024-06-25 01:49:13 +08:00
hiyouga
135bfbf7c1 tiny fix
Former-commit-id: bb57478366a70a0871af30ab31c890f471e27ff4
2024-06-25 01:15:19 +08:00
hoshi-hiyouga
5cfcb8262e Merge pull request #4417 from mMrBun/main
Add tool_format parameter to rewrite templates for different function call formats.

Former-commit-id: 8d1460cad5bff5e4626fdd675046021e0a3d1947
2024-06-24 23:17:55 +08:00
hiyouga
a79e93f335 fix #4410
Former-commit-id: f49adc4ab5eade21d7a9e029212f17688ee9b0cf
2024-06-24 22:34:31 +08:00
hoshi-hiyouga
d475dd3809 Update parser.py
Former-commit-id: 60e605cd9d399bd04432864ede9c84302890eac8
2024-06-24 21:37:42 +08:00
stceum
16e950454e Bug Fix: off is parsed as False in yaml file, changed to disabled to avoid this.
Former-commit-id: 171289d8e4c111fdca2b100282b64c74a04a4726
2024-06-24 20:39:31 +08:00
mMrBun
43a065bb07 Add tool_format to overwrite tool formatter template
Former-commit-id: af08971ca50443fd5597e5e4412a3aa17214502f
2024-06-22 02:13:23 +08:00
ancv
6c185a2c57 move configure_packing to llamafactory.model.patcher and fix constants
Former-commit-id: 9c5e972c9c81957f2e9e30bf284ef1c076de9fd0
2024-06-21 00:45:06 +07:00
hiyouga
af2cb33bb2 tiny fix
Former-commit-id: 2d8d47f6126d68db1701ed18fc31310c6f14dd49
2024-06-20 22:56:05 +08:00
Jonery
fa3150548e Cleaner integration.
Former-commit-id: 26d4b05d424bd71f570195dd433258caf6465d92
2024-06-19 12:29:40 +08:00
hiyouga
4bc0bea0e9 fix #4357
Former-commit-id: a6741bba8cebd16a6a3f97a2dc81057d0e27eb39
2024-06-18 22:42:45 +08:00
Jonery
870a54ac84 fix typo
Former-commit-id: d4bee3716dbf8a84564d5bcc2059172604819f3e
2024-06-18 12:39:26 +08:00
Jonery
12fcfc2b72 Support distributed BAdam.
Former-commit-id: bdcb986e37975911c190a74d3e60bb77aa2033bd
2024-06-18 12:27:47 +08:00
hiyouga
875270b851 lint
Former-commit-id: a19a7ac99af62b6715c96274f6350b124a784331
2024-06-17 22:35:56 +08:00
Jonery
95ae30f678 Merge remote-tracking branch 'upstream/main'
Former-commit-id: 37834a7e79473ccf50ad7f67745b97c274c326d9
2024-06-17 18:44:51 +08:00
Jonery
ba303fd1aa adapt for badam with ds zero3
Former-commit-id: fff2a020ec8713022bd8145f4a7168168ea07ca4
2024-06-17 18:18:10 +08:00
hoshi-hiyouga
ca67b7a568 Update parser.py
Former-commit-id: d10c97193d08bd368aca1a72f0d1d8a96c76765d
2024-06-16 02:57:00 +08:00
hiyouga
32f45c9e91 support pissa
Former-commit-id: ef8e45f2eaf466c54e9a671512a2974575677b08
2024-06-16 01:08:12 +08:00
hiyouga
05f3a3c944 tiny fix
Former-commit-id: f7f440986b0ae3b38ea9f2da80789629d4f79ea1
2024-06-16 01:06:41 +08:00
hiyouga
14f7bfc545 use fixture
Former-commit-id: 10761985691b9f934f7689c1f82aa6dd68febcca
2024-06-15 20:06:17 +08:00
hiyouga
bb88536166 add license
Former-commit-id: 69cfc98d7c81756a5ab6bf962240e393e449fef0
2024-06-15 17:54:33 +08:00
hiyouga
2af932d969 disable DP
Former-commit-id: c18fd609d268389f3e65274992045a6c9f8e6c1f
2024-06-15 04:57:19 +08:00
hiyouga
3ff9b87012 add test cases
Former-commit-id: 731176ff34cdf0cbf6b41c40c69f4ceb54c2daf6
2024-06-15 04:05:54 +08:00
hiyouga
5080f2314c fix lint
Former-commit-id: b170165679317af2b3f03633afac27661b3deb06
2024-06-13 00:48:44 +08:00
ancv
c7ab302c69 implement efficient packing without cross-contamination attention
Former-commit-id: a64a5305c0da5ef092d4cc26faf829bb44de65d1
2024-06-12 11:56:01 +07:00
hiyouga
820b6e7b32 fix #4198
Former-commit-id: 945d2c6cc73542adf9272ebd9aa332ea2c1c7361
2024-06-11 15:38:38 +08:00
hiyouga
27aece94cf tiny fix
Former-commit-id: c4b2e263d9cefbad0fbc5de72422e4ef8edbcb54
2024-06-11 12:48:53 +08:00
hiyouga
ff9ba70bb8 reorganize adapter code
Former-commit-id: b26c2df9d97f4efffccbf7d28de13619b43f10dd
2024-06-08 00:47:23 +08:00
hiyouga
937f49ec3d lora modules: all by default
Former-commit-id: 52c4ae87c7f4312704c31ef26b079b2c5b95ea5f
2024-06-06 03:53:28 +08:00
hoshi-hiyouga
c709d5f7db Merge pull request #4080 from MengqingCao/npu
Add npu option for model exporting

Former-commit-id: 07fc67193ef6bcb8e8a392aff0c57a2eb36832bf
2024-06-06 03:15:44 +08:00
hoshi-hiyouga
ee5853c565 Update model_args.py
Former-commit-id: 09c0afd94a8a5f5b45a61b32c983d50e1b9e2941
2024-06-06 03:14:23 +08:00
hiyouga
fc95800840 add vllm_dtype arg #3387 #3717
Former-commit-id: a0dd3a6351bb78541d40fec1d2fc457d803c86a4
2024-06-06 02:53:27 +08:00
hiyouga
765715af21 support train from scratch #4033 #4075
Former-commit-id: 1290b9d01077e62f8de7a23637daa2586cc82bfa
2024-06-06 02:43:19 +08:00
MengqingCao
9dd5f7d642 add npu for model export
Former-commit-id: ce020b6eb3f35c1db37ee4835e694eddcd0f59b0
2024-06-05 07:06:40 +00:00
hiyouga
82d744716a fix #4005 #4013
Former-commit-id: 8608fa268cde5cddf8d0c6c2eb2cb5fa246c1831
2024-06-03 19:12:29 +08:00
hoshi-hiyouga
1a3764ab8f Merge pull request #4007 from xu-song/patch-3
Update model_args.py

Former-commit-id: d88b3a0f2707bcc964f642d348295b99f7c796f8
2024-06-03 18:54:37 +08:00