Commit Graph

88 Commits

Author SHA1 Message Date
codingma 76f3bbcfc0 1. add custom eval dataset support
2. merge load dataset and split dataset function
2024-07-05 15:52:10 +08:00
hiyouga 344b9a36b2 tiny fix 2024-06-18 23:32:18 +08:00
Eli Costa 74e49cca95
Add Magpie and Webinstruct dataset samples
Adds two dataset samples claimed superior performance: Magpie (from Allen AI) and Webinstruct (from TIGER-Lab).
2024-06-15 19:31:56 -03:00
hiyouga c7a5620ccc add neo-sft dataset 2024-06-13 01:00:56 +08:00
hiyouga 12d79f89c5 add ultrafeedback and fineweb #4085 #4132 2024-06-08 02:42:34 +08:00
hiyouga 08564838bd fix full/freeze tuning for mllm 2024-05-27 20:37:57 +08:00
BUAADreamer 576b0206c2 Merge branch 'main' of https://github.com/BUAADreamer/LLaMA-Factory 2024-05-27 20:11:23 +08:00
BUAADreamer e2022ce4e9
Merge branch 'hiyouga:main' into main 2024-05-27 20:10:58 +08:00
BUAADreamer f665342a27 remove mllm_pt_demo.json 2024-05-27 20:10:31 +08:00
hiyouga 08bd0440b5 add llava 1k datasets 2024-05-27 19:57:33 +08:00
BUAADreamer 29a6d5bdb8 support pretraining of llava 2024-05-21 08:57:14 +08:00
hiyouga c450ee87a3 improve KTO impl., replace datasets 2024-05-18 03:44:56 +08:00
enji.zhou db1d5a4f51 add kto 2024-05-17 13:09:17 +08:00
hiyouga 58c522cd5c remove checksum and fix ui args 2024-05-12 01:10:30 +08:00
codingma d5520b6017 fix sha1 of glaive_toolcall dataset 2024-05-09 16:33:45 +08:00
hiyouga 1ccbfe562d remove big file 2024-05-07 22:14:06 +08:00
hiyouga 09f3ef1de4 fix stop param 2024-05-07 00:41:04 +08:00
hoshi-hiyouga d6ca7853fa
Merge pull request #3588 from ZeyuTeng96/patch-1
update hf_hub_url for nectar_rm in dataset_info
2024-05-07 00:06:11 +08:00
hoshi-hiyouga c3910ab98a
Update dataset_info.json 2024-05-07 00:05:45 +08:00
hiyouga f02f87c6fb update example docs 2024-05-06 22:51:02 +08:00
ZeyuTeng96 044af36442
update hf_hub_url for nectar_rm in dataset_info
Hi there,

I cannot find the "mlinmg/RLAIF-Nectar" on hf, seems like it changed as "AstraMindAI/RLAIF-Nectar". So, making a PR for updating.

See: https://huggingface.co/datasets/AstraMindAI/RLAIF-Nectar
2024-05-06 16:44:50 +08:00
hiyouga 5ee04d418c update readme 2024-04-26 23:39:19 +08:00
hoshi-hiyouga 8f91420223
Merge pull request #3471 from BUAADreamer/main
add llava_150k en/zh mllm sft data
2024-04-26 23:36:41 +08:00
hoshi-hiyouga c29b257007
Update dataset_info.json 2024-04-26 23:34:34 +08:00
BUAADreamer a177872010 add llava_150k en/zh mllm sft data 2024-04-26 23:18:58 +08:00
hiyouga 168f56683a release v0.7.0 2024-04-26 23:18:00 +08:00
hiyouga e057c8de48 support mllm hf inference 2024-04-26 05:34:58 +08:00
hoshi-hiyouga f8c26e6a34
Update dataset_info.json 2024-04-26 03:03:36 +08:00
BUAADreamer 42c90c8183 merge data part to the text stream 2024-04-25 19:58:47 +08:00
BUAADreamer c6dd89918f merge data part to the text stream 2024-04-25 19:19:59 +08:00
BUAADreamer cfb485eddf add llava and instructblip 2024-04-25 00:22:43 +08:00
BUAADreamer 4dcb11eab7 add multimodal LLM BLIP-2 and InstructBLIP 2024-04-23 18:45:43 +08:00
hiyouga 6339edefff add dpo mix dataset 2024-04-20 01:31:38 +08:00
hiyouga d1fb6c72b5 fix #3247 2024-04-12 17:41:33 +08:00
li.yunhao 9c2ef9cdf4 fix pile datset hf hub url 2024-03-30 16:06:10 +08:00
hiyouga 3271af2afc add orca_dpo_pairs dataset 2024-03-20 20:09:06 +08:00
hiyouga 894d183214 update readme, add starcoder2, cosmopedia 2024-03-03 01:01:46 +08:00
hiyouga 32884523c5 update data 2024-03-02 19:37:18 +08:00
hiyouga 1630a4cb8f fix #2533 2024-02-21 22:47:48 +08:00
hiyouga 22acab8aff fix #2481 2024-02-15 19:07:47 +08:00
hiyouga 7d2dc83c5e improve aligner 2024-02-10 16:39:19 +08:00
Mark Mueller 1d3598afa1 Slim Orca data parsing 2024-02-08 19:32:20 +01:00
Johann-Peter Hartmann 49c69ea4b9 WS fix 2024-02-06 20:13:04 +01:00
Johann-Peter Hartmann 1126563505 add ranking to dpo dataset 2024-02-06 20:12:36 +01:00
Johann-Peter Hartmann 870182c3a9 remove comma 2024-02-03 08:48:39 +01:00
Johann-Peter Hartmann d9a8301ed4 Add support for german datasets 2024-01-30 10:18:01 +01:00
hiyouga dbaaa4546e Update dataset_info.json 2024-01-23 00:10:32 +08:00
hiyouga f1067d2b58 enable cutoff len 2024-01-18 12:25:42 +08:00
hiyouga d9f1cae351 support function calling 2024-01-18 09:54:23 +08:00
hiyouga 5b93d545e2 tiny update 2023-12-25 18:29:34 +08:00