40 Commits

Author SHA1 Message Date
hiyouga
c0e887c85a update training resuming
Former-commit-id: 2ec75c31f609e65116ac3b621eeb7d8ccbf69135
2023-08-18 01:41:17 +08:00
hiyouga
ff5ebb6a86 support bf16 ppo #551
Former-commit-id: 092088967de7409a2d51847cfc7afc83a8887320
2023-08-18 00:40:32 +08:00
hiyouga
4d6534a665 alert pad_token source
Former-commit-id: f26a84e0d927d2554890daf431a93652e18f4235
2023-08-15 00:07:56 +08:00
hiyouga
1ce4a6109f fix ChatGLM lm_head #494
Former-commit-id: bf0048abdaeb2b9592d38ac991704ad014370b47
2023-08-14 14:14:48 +08:00
hiyouga
03537dda06 tiny fix
Former-commit-id: 50a34c043de6d9e1410291e1d8c1ea9d53754e9e
2023-08-12 22:02:43 +08:00
hiyouga
4bbbee4370 fix rope scaling
Former-commit-id: 2e0dd36700ec5e8294581c1db4b9431f755fc5f8
2023-08-12 22:00:01 +08:00
hiyouga
56d6448c4a update readme
Former-commit-id: 6fa381400c21fa249cebcdff8c3afd72f8de20b3
2023-08-12 21:00:11 +08:00
hiyouga
a15a602809 support rope scaling, fix #475 #476 #478
Former-commit-id: 337d5f68b72230e545e7a94ca789187c7a2b7187
2023-08-12 20:46:27 +08:00
hiyouga
9644286027 fix unusual output of 8bit models #278 #391
Former-commit-id: 337ce5272b81f5561162beb08814b0e5abf23703
2023-08-12 00:25:29 +08:00
hiyouga
98aa629843 Release v0.1.6
Former-commit-id: 43c8b3c3c8bfb2e32d17fb3e8b194938e37d54bd
2023-08-11 23:25:57 +08:00
hiyouga
7ada4f5f6f support DPO training (2305.18290)
Former-commit-id: 6d98de148e4af63a7028dfaeb6cf86eb56a4488f
2023-08-11 03:02:53 +08:00
hiyouga
6eb4120464 support val set in streaming mode
Former-commit-id: faed15b58ed00b1e09bb091e7eee48f5ef7c508b
2023-08-09 23:00:26 +08:00
hiyouga
b6316b460f fix tokenizer #417
Former-commit-id: 01aa678311bfd213a4b410a4e0ff09f48a0d40a1
2023-08-08 23:59:41 +08:00
hiyouga
5ada0ee44c fix bug
Former-commit-id: c13ce66021b21e015871b84489eeafa127a424a4
2023-08-08 17:55:55 +08:00
hiyouga
ab66cc8e37 fix chatml template #408
Former-commit-id: 21e0cc3f44c35ae689b00b274391492f413725ac
2023-08-08 17:44:39 +08:00
hiyouga
1ede9595c1 fix #376
Former-commit-id: a5b01257ba3323bcb2dd0217fb89a387e39ddbec
2023-08-07 13:58:59 +08:00
hiyouga
1d0ccf63f2 update trainer
Former-commit-id: 0d39b53a5164e34d22fe0a492eaa0d7ac63102fe
2023-08-07 13:34:35 +08:00
hiyouga
577b3cd0de fix qwen eos token
Former-commit-id: 770830c67886f5872b39b9608949ec62d4616b27
2023-08-06 13:31:17 +08:00
hiyouga
2d153e35ef fix mtloader
Former-commit-id: ca48c2c02c3cfa9afb99971b50daeda9cf14e7cb
2023-08-03 19:29:02 +08:00
hiyouga
7358098e32 fix qwen inference
Former-commit-id: 823f0de0ca0a92b6f48a90e5ffe57a48dc018f1d
2023-08-03 16:31:55 +08:00
hiyouga
bf15c4a03c support Qwen-7B, fix InternLM-7B inference
Former-commit-id: 25d2ca29ecb70cbfd5206333c667042a0c4d2e5a
2023-08-03 15:53:32 +08:00
hiyouga
4c37e03ca6 fix webui
Former-commit-id: e87630ef77977b2879f1199b9a421acbbbb32a51
2023-08-03 12:43:12 +08:00
hiyouga
2fdef55143 update ppo trainer
Former-commit-id: c27136a83e167465d3f825e40f10c7b9fcfbf97a
2023-08-02 18:46:41 +08:00
hiyouga
ab3f685330 fix RM save model
Former-commit-id: 8104cc2425431eb1cddccf3909855296116f922b
2023-08-01 11:56:17 +08:00
hiyouga
5faad2a64c release v0.1.4
Former-commit-id: 81f84aaf2e120e39edb28ef42893939fc9a184e2
2023-08-01 10:08:47 +08:00
hiyouga
44c31d6064 fix inference
Former-commit-id: 55dc2bdd3eaa552c655e584fc3cbbf017c7bc3e7
2023-08-01 00:06:48 +08:00
hiyouga
1c2422df31 fix arg check
Former-commit-id: 2c5c73de9ebc88e2d04e80754781c94a571133a0
2023-07-31 23:48:57 +08:00
hiyouga
5cab5c1b36 update readme
Former-commit-id: d99cda254e5025ff3f968d256197ab031bfabef1
2023-07-31 23:42:32 +08:00
hiyouga
63123a9098 support streaming data, fix #284 #274 #268
Former-commit-id: 819cc1353599e5fa45658bc56dd0dbe4b258b197
2023-07-31 23:33:00 +08:00
hiyouga
913284c29f fix #242
Former-commit-id: 80a346e29beb49e8935b786e2af1059fdc4954b2
2023-07-25 17:04:02 +08:00
hiyouga
36d04e248e release v0.1.3
Former-commit-id: 62c68bcbf591516e8f90b47810bea6f710fd23f6
2023-07-21 16:48:34 +08:00
hiyouga
3855557f8c fix save function
Former-commit-id: 1d6beb0c8490a7531ffdf7a2819410597b200d12
2023-07-21 14:09:07 +08:00
hiyouga
1f4a65afea update web UI, support rm predict #210
Former-commit-id: 92cc6b655dc91b94d5bf9d8618c3b57d5cf94333
2023-07-21 13:27:27 +08:00
hiyouga
27b8d690e5 tiny fix
Former-commit-id: 22b1be7bbb9e7bd863acb88bf7365090b1b8235d
2023-07-19 22:53:46 +08:00
hiyouga
139f83aacd fix #199
Former-commit-id: 7fc778b49bc17688aca39fffe01f9d33e03e0c28
2023-07-19 22:51:29 +08:00
hiyouga
53d7d4c221 release v0.1.0
Former-commit-id: 63c8d3a17cb18f0d8a8e37bfa147daf5bdd28ea9
2023-07-18 00:18:25 +08:00
hiyouga
72058cc816 fix #175
Former-commit-id: fd557ebb5e3ef2ca330b4d97731af43f4a5a5fc5
2023-07-17 18:07:17 +08:00
hiyouga
b9d33cd3a1 fix saving custom code
Former-commit-id: 3f8f40bffd4f61fcc045f5f8a07420f3b46d0f7a
2023-07-16 18:04:41 +08:00
hiyouga
75a97a3991 fix callback
Former-commit-id: 065680cd2a410d7ceab10a4a76588df43e286117
2023-07-15 17:18:16 +08:00
hiyouga
a69b1b1c3a modity code structure
Former-commit-id: 0682ed357210897e0b67c4a6eb31a94b3eb929f1
2023-07-15 16:54:28 +08:00