42 Commits

Author SHA1 Message Date
hiyouga
3f0a2d6adc support rope scaling, fix #475 #476 #478
Former-commit-id: fa940c17b8d3e379af08804003f1a522c1cd6ac4
2023-08-12 20:46:27 +08:00
hiyouga
7bd4c59b7e fix unusual output of 8bit models #278 #391
Former-commit-id: dd51c242032ce3f878cb191dc144536db4a2bb45
2023-08-12 00:25:29 +08:00
hiyouga
79f4ba0d26 Release v0.1.6
Former-commit-id: a48cb0d474ef0648a97387daf5f623498b5e3ee6
2023-08-11 23:25:57 +08:00
hiyouga
abdfa26d06 support DPO training (2305.18290)
Former-commit-id: 3ec4351cfdaf2aefcc7d13345e19d79874ed61d3
2023-08-11 03:02:53 +08:00
hiyouga
6404167ab7 support val set in streaming mode
Former-commit-id: d86ea314a197fd821770d895e988c48d46679047
2023-08-09 23:00:26 +08:00
hiyouga
b43f37ca19 fix sft trainer
Former-commit-id: df946e6949c77179a5080b780109e22c297caef8
2023-08-09 16:35:03 +08:00
hiyouga
77aa9853fb fix tokenizer #417
Former-commit-id: eecc4b2131e88b38fcd2659b52799a2f6459822f
2023-08-08 23:59:41 +08:00
hiyouga
70b53d9503 fix bug
Former-commit-id: 4b841a6b35585120c65e2718d6002c69cc40b925
2023-08-08 17:55:55 +08:00
hiyouga
c796c542c8 fix chatml template #408
Former-commit-id: a9980617f5c6e3356b672c8635696b2f2e308a5e
2023-08-08 17:44:39 +08:00
hiyouga
871f7de3d0 fix #376
Former-commit-id: 081345baca263b5f0a6e936e71605e7cb127b3cd
2023-08-07 13:58:59 +08:00
hiyouga
77f6647e8f update trainer
Former-commit-id: 220175ab2410ce22a553344eb75d5a556ed1a276
2023-08-07 13:34:35 +08:00
hiyouga
2faa1af4eb fix qwen eos token
Former-commit-id: e21ae0135610bad8116cadbe4b184aac8e279d7c
2023-08-06 13:31:17 +08:00
hiyouga
0328c0e07c fix mtloader
Former-commit-id: a0173c427dacd96fac2fcffc23639d270721fdef
2023-08-03 19:29:02 +08:00
hiyouga
788d1250c1 fix qwen inference
Former-commit-id: 2780792754b484bf4d42af5ebbc51c7ed2181ce9
2023-08-03 16:31:55 +08:00
hiyouga
9c84c4ed5d support Qwen-7B, fix InternLM-7B inference
Former-commit-id: 87f8f830e20aa839e089559c1d038954742000ef
2023-08-03 15:53:32 +08:00
hiyouga
91d178f14d fix webui
Former-commit-id: e23a3a366c5419506bf18bebcb2d679b87e7976b
2023-08-03 12:43:12 +08:00
hiyouga
4242897b78 modify code structure
Former-commit-id: 08f180e78862cad902b6cdbbd8c86e39b5cacf8a
2023-08-02 23:17:36 +08:00
hiyouga
4b8e4398bc fix PPO trainer
Former-commit-id: 1d8a1878ea053d1dbfc570eea868d2514ce75a51
2023-08-02 19:10:23 +08:00
hiyouga
569df8ccd6 update ppo trainer
Former-commit-id: b5ba87952ab02ed0720365ebd571e47e92e1cda6
2023-08-02 18:46:41 +08:00
hiyouga
ab739e72ea fix memory leak of PPO trainer
Former-commit-id: 286f7be346dbea630da1642bbc9e98bcad3145b4
2023-08-02 17:41:34 +08:00
hiyouga
c5ad96375e fix RM save model
Former-commit-id: ac88ce5233248dbf1c7943c5f1197e40ba52fde9
2023-08-01 11:56:17 +08:00
hiyouga
aa4335eac7 release v0.1.4
Former-commit-id: 973a6386657885c7d11ecc8746ebd8804b6b355d
2023-08-01 10:08:47 +08:00
hiyouga
e34fc5fd2e fix inference
Former-commit-id: d3a0692d4d9033a3b58d68357294854144479536
2023-08-01 00:06:48 +08:00
hiyouga
d5d3b2a42f fix arg check
Former-commit-id: 9cb1f119a4757c4fd2dc6db9335589d94f6ab5eb
2023-07-31 23:48:57 +08:00
hiyouga
a437424381 update readme
Former-commit-id: 62dca5bb820b8e75f3e24294d578322b97303b5f
2023-07-31 23:42:32 +08:00
hiyouga
e80b75b560 support streaming data, fix #284 #274 #268
Former-commit-id: 0411a4b3e122e7907441bc7a64b004948741a620
2023-07-31 23:33:00 +08:00
hiyouga
c52dd3e86f fix #242
Former-commit-id: 00efa8a07fe5a69bac545675696b2a19b7b811ed
2023-07-25 17:04:02 +08:00
hiyouga
ee7aa86312 release v0.1.3
Former-commit-id: 0b6150bc31b5a1be3a269af971c3827ae8cc5aac
2023-07-21 16:48:34 +08:00
hiyouga
daf81288a1 fix save function
Former-commit-id: d2f18197e379601a60fa878af975c68d7c8b9648
2023-07-21 14:09:07 +08:00
hiyouga
f769c2d3fc update web UI, support rm predict #210
Former-commit-id: ed0e186a134de816d6a9278f4e47baa6250a52d1
2023-07-21 13:27:27 +08:00
hiyouga
64b4f71673 simplify code
Former-commit-id: 67a27730744b71795b10260d050501bfe2329c26
2023-07-20 15:08:57 +08:00
hiyouga
106802390b tiny fix
Former-commit-id: d1d8e8bae13367ae59c3aa4058aa7d51378af632
2023-07-19 22:53:46 +08:00
hiyouga
a12785fd9b fix #199
Former-commit-id: d111e658a29a70b9f3fd4c18c35eaf3f8a5ae109
2023-07-19 22:51:29 +08:00
hiyouga
1a23cb2578 fix #196
Former-commit-id: 925a790bc9507c4d23af275a5abfb149959dbdcb
2023-07-19 17:35:38 +08:00
hiyouga
18656a6316 fix API
Former-commit-id: 29af67b015ff92e5dd9bf2985ce7723dc036d989
2023-07-19 00:01:14 +08:00
hiyouga
af37ac077c support dev set in web ui
Former-commit-id: fe2887ca1304e5b5cfd7fbd820a9a0c8dedd23ef
2023-07-18 20:40:49 +08:00
hiyouga
0b6f769971 update webUI, fix #179
Former-commit-id: 12d8a8633f1d8db8eb72223f69c074d98af16e01
2023-07-18 15:35:17 +08:00
hiyouga
091805d38e release v0.1.0
Former-commit-id: f8193e8009451cf569a28a10eb4bd88831844441
2023-07-18 00:18:25 +08:00
hiyouga
799524b37b fix #175
Former-commit-id: 85c2210452cc45470c228f17b2b0df09b47e9575
2023-07-17 18:07:17 +08:00
hiyouga
c4f1d98a1c fix saving custom code
Former-commit-id: 1e1358431dde1ed774b0e1e48760ca9f0db685ef
2023-07-16 18:04:41 +08:00
hiyouga
70b5232f9a fix callback
Former-commit-id: 22d9a9c2af6674eb832ae4aee80d679f19b7006f
2023-07-15 17:18:16 +08:00
hiyouga
a696148d6b modity code structure
Former-commit-id: f75137661358f9070bc70c341dfa2cc5fd69cf94
2023-07-15 16:54:28 +08:00