mirrors / artidoro--qlora

提交

提交图

  • 7f4e95a68d Merge pull request #183 from AlpinDale/patch-2 main Artidoro Pagnoni 2023-07-24 02:11:34 -07:00
  • eee4f88f29 Merge pull request #178 from ranchlai/main Artidoro Pagnoni 2023-07-24 02:07:58 -07:00
  • 5486baa59a Merge branch 'main' into main Artidoro Pagnoni 2023-07-24 02:07:28 -07:00
  • 76d86645b8 Merge pull request #219 from abhilash1910/main Artidoro Pagnoni 2023-07-24 01:25:03 -07:00
  • 82c730a48a Merge pull request #143 from bubundas17/patch-1 Artidoro Pagnoni 2023-07-24 01:15:44 -07:00
  • 965f8b3430 generage example Artidoro Pagnoni 2023-07-23 15:04:07 -07:00
  • 6c6fc4653a Merge pull request #220 from artidoro/llama2 Artidoro Pagnoni 2023-07-19 06:21:46 -07:00
  • b0d2fe0dc2 cleanup llama2 Artidoro Pagnoni 2023-07-19 06:20:03 -07:00
  • 68ff19681f example llama2 finetuning Artidoro Pagnoni 2023-07-19 04:54:48 -07:00
  • 4a3e5ddc0f Merge pull request #217 from ffohturk/main Artidoro Pagnoni 2023-07-19 04:15:38 -07:00
  • a9644b4154 xpu support abhilash1910 2023-07-19 04:01:03 -07:00
  • a17d93e6fd xpu support abhilash1910 2023-07-19 00:47:53 -07:00
  • 61dfbe287e Updated qlora.py ffohturk 2023-07-19 02:03:36 +03:00
  • 190d22aa4b Merge pull request #215 from artidoro/embeddingfix Artidoro Pagnoni 2023-07-18 11:47:58 -07:00
  • 5111741384 freezing embeddings and known issue embeddingfix Artidoro Pagnoni 2023-07-18 04:22:33 -07:00
  • 845188de11 Update README.md Artidoro Pagnoni 2023-07-17 09:00:28 -07:00
  • 0fc40da9dc Enhances GPU bfloat16 support check AlpinDale 2023-06-22 16:06:06 +00:00
  • af90b31d5a add trust_remote_code for AutoTokenizer ranchlai 2023-06-19 00:44:14 +08:00
  • 6d6a2ed677 Merge branch 'artidoro:main' into patch-1 Bubun Das 2023-06-09 22:02:16 +05:30
  • cc488110b5 human ratings artidoro 2023-06-08 13:20:51 -07:00
  • 9c6e450468 Fixed Local .jsonl dataset loading Bubun Das 2023-06-08 00:18:53 +05:30
  • 3da535abdf Merge pull request #101 from dameikle/main Artidoro Pagnoni 2023-06-06 11:49:29 -07:00
  • 4ea02e7464 Merge pull request #126 from tobi/rank-and-files Artidoro Pagnoni 2023-06-06 11:43:50 -07:00
  • f4ee7fd786 Update qlora.py Artidoro Pagnoni 2023-06-06 11:31:24 -07:00
  • 00e5ad2a75 pandas is better at reading lines Tobias Lütke 2023-06-03 19:46:39 -04:00
  • bed4b0d863 typo Tobias Lütke 2023-06-03 19:42:49 -04:00
  • e69303d556 introduce LOCAL_RANK mapping and optiojn to leave input data as-is Tobias Lütke 2023-06-03 19:30:39 -04:00
  • bdc655dfa7 Merge pull request #102 from steremma/steremma-patch-1 Artidoro Pagnoni 2023-06-01 07:37:40 -07:00
  • 986c500c5b Respect cache_dir passed by user Stergiadis Manos 2023-06-01 13:40:55 +02:00
  • 86ac6016f6 Update the scripts with HF checkpoints Artidoro Pagnoni 2023-05-31 22:44:30 -07:00
  • 8ee760d80e Added use_auth_token to model arguments to load private models David Meikle 2023-06-01 06:14:32 +01:00
  • 43643cab5d Reordering README.md Artidoro Pagnoni 2023-05-31 20:22:15 -07:00
  • e598fe8f8f multi-gpu discussion Artidoro Pagnoni 2023-05-31 20:20:00 -07:00
  • 0b46ca80a0 add guanaco repro scripts Artidoro Pagnoni 2023-05-31 20:17:51 -07:00
  • a45718eec2 fix tokenization issues Artidoro Pagnoni 2023-05-31 19:52:43 -07:00
  • 5f618e7e90 oasst1 and bug fixes Artidoro Pagnoni 2023-05-31 18:16:00 -07:00
  • 460525b4fe gitignore Artidoro Pagnoni 2023-05-31 18:12:47 -07:00
  • d69e26db70 requirements Artidoro Pagnoni 2023-05-31 16:41:22 -07:00
  • 94e50419e3 Merge pull request #86 from dred0n/feature-local-training-data Artidoro Pagnoni 2023-05-31 14:27:33 -07:00
  • d9f201c2b6 Merge pull request #79 from KKcorps/resume_patch Artidoro Pagnoni 2023-05-31 14:22:00 -07:00
  • 9991dc555c Update README.md Artidoro Pagnoni 2023-05-30 13:34:46 -07:00
  • 7e1e81445b Merge pull request #44 from KKcorps/empty_adapter_patch Artidoro Pagnoni 2023-05-30 11:56:00 -07:00
  • ace51b6e34 add jsonl local dataset support Dredon 2023-05-30 10:45:11 -05:00
  • 2e21c16297 add csv, tsv support Dredon 2023-05-30 09:43:49 -05:00
  • c06d702e5f add support local training set support Dredon 2023-05-30 08:52:20 -05:00
  • 163adf26a6 Only load adapter weights on resume KKCorps 2023-05-29 14:51:01 +05:30
  • f96eec1675 Merge pull request #63 from pmysl/main Artidoro Pagnoni 2023-05-28 13:46:32 -07:00
  • e31aedd4ba Suppress pad_token warning message Piotr Myśliński 2023-05-28 14:00:12 +02:00
  • ce5e5be9de Merge pull request #58 from muelletm/patch-1 Artidoro Pagnoni 2023-05-27 20:32:24 -07:00
  • 204dda82c4 Merge pull request #51 from pmysl/main Artidoro Pagnoni 2023-05-27 20:29:42 -07:00
  • af55cf0c62 Merge pull request #20 from Qubitium/check-llama Artidoro Pagnoni 2023-05-27 20:23:17 -07:00
  • a3809620ee Adding guanaco openassistant dataset Artidoro Pagnoni 2023-05-27 17:01:08 -07:00
  • 3926ee5c02 Update finetune.sh Thomas Müller 2023-05-27 20:33:23 +02:00
  • 530382b430 Fix link to inference notebook Piotr Myśliński 2023-05-27 10:32:46 +02:00
  • f1d1b2901a Remove resetting old state to fix empty adapters KKCorps 2023-05-26 22:02:16 +05:30
  • 073a4856f9 Update README.md Artidoro Pagnoni 2023-05-25 12:13:57 -07:00
  • 8532e0117d Check for LlamaTokenizerFast rather than infer type from path name. Fix cases where non-standard llama model path names gets bypassed in tokenizer check. The tokenizer is init with use_fast=True and qlora requires >4.29.2 transformers so the only possible tokenizer is LlamaTokenizerFast. Qubitium 2023-05-25 07:00:32 +00:00
  • e3817441cc fast demo Artidoro Pagnoni 2023-05-24 08:36:26 -07:00
  • a472fa1af0 demo info Artidoro Pagnoni 2023-05-24 08:04:05 -07:00
  • 3ba09cba37 Update README.md Artidoro Pagnoni 2023-05-24 07:37:50 -07:00
  • 55c643ed69 added demo links Artidoro Pagnoni 2023-05-24 07:24:35 -07:00
  • cc962c9e61 demo notebook Artidoro Pagnoni 2023-05-24 07:00:10 -07:00
  • a757cb1164 gradio colab demo Artidoro Pagnoni 2023-05-24 06:43:55 -07:00
  • bbbfc81ef0 installation info Artidoro Pagnoni 2023-05-24 05:14:49 -07:00
  • 3c0358774b distinguish gpt vs guanaco Artidoro Pagnoni 2023-05-24 04:55:39 -07:00
  • dd9a2c4651 Update README.md Artidoro Pagnoni 2023-05-24 01:24:30 -07:00
  • 088f9265ea adding qualitative example notebook Artidoro Pagnoni 2023-05-24 01:17:46 -07:00
  • 6f91610405 adding qualitative example notebook Artidoro Pagnoni 2023-05-24 01:15:52 -07:00
  • dd24451106 qualitative analysis comparison Artidoro Pagnoni 2023-05-24 01:09:22 -07:00
  • 5dc04ee367 evaluation main readme rephrase Artidoro Pagnoni 2023-05-24 00:45:33 -07:00
  • 05daee4ead eval information Artidoro Pagnoni 2023-05-24 00:41:49 -07:00
  • ccdea9d783 more eval and rating Artidoro Pagnoni 2023-05-23 23:15:57 -07:00
  • 494e51433b installation info coming soon Artidoro Pagnoni 2023-05-23 22:12:29 -07:00
  • 50af4c60e7 generations vicuna and oa Artidoro Pagnoni 2023-05-23 22:01:29 -07:00
  • 046b26e387 fixing abstract Artidoro Pagnoni 2023-05-23 21:20:00 -07:00
  • 8d975d6405 Update README.md Artidoro Pagnoni 2023-05-23 19:19:45 -07:00
  • 6770026c18 General repo info and paper link Artidoro Pagnoni 2023-05-23 17:54:35 -07:00
  • 9f684a4c8c Merge pull request #2 from scottlogic-alex/support-mpt Artidoro Pagnoni 2023-05-22 11:19:44 -07:00
  • ac4dfd84c2 Merge pull request #1 from scottlogic-alex/logger-fix-rebase Artidoro Pagnoni 2023-05-22 11:18:31 -07:00
  • 7e4b88cbaf remove broken logger.log() call (was not specifying which log level to use). put the message in the error instead. Alex Birch 2023-05-22 18:37:22 +01:00
  • 765455f2d6 support trusting remote code (to unpickle MPT-based models) Alex Birch 2023-05-22 18:34:31 +01:00
  • 132e0510f0 rename and cleanup Artidoro Pagnoni 2023-05-12 12:14:23 -07:00
  • a73df93f89 Cleanup. Tim Dettmers 2023-05-12 05:29:17 -07:00
  • 3227a4f50a Remove print. Tim Dettmers 2023-05-12 05:25:47 -07:00
  • 10f17b5e27 Merge branch 'main' of github.com:artidoro/fromo into main Tim Dettmers 2023-05-12 05:18:46 -07:00
  • c90995f5b5 Added default hyperparamters. Tim Dettmers 2023-05-12 05:18:31 -07:00
  • f15c29fb9e Update README.md Artidoro Pagnoni 2023-05-11 22:27:33 -07:00
  • bd7c3012c9 Update README.md Artidoro Pagnoni 2023-05-11 21:58:10 -07:00
  • 0446e016b6 Removed some hardcoded paths. Tim Dettmers 2023-05-11 21:37:52 -07:00
  • f0178a439a clean Artidoro Pagnoni 2023-05-11 12:20:38 -07:00
  • 8a74465dc9 fix generation Artidoro Pagnoni 2023-05-11 12:07:07 -07:00
  • e7d8fb83ce finetune_llama Artidoro Pagnoni 2023-05-11 07:15:41 -07:00
  • ae4ca6e4a0 Initial commit Artidoro Pagnoni 2023-05-11 02:30:23 -07:00