wassname/peft
1
0
Fork 0
mirror of https://github.com/wassname/peft.git synced 2026-09-26 14:00:37 +08:00
Code Issues Packages Projects Releases Wiki Activity
290 Commits 1 Branch 0 Tags
d49cde41a7d62cc5e42b259430e95a6a1bc99e44
Commit Graph
290 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
MKhalusova d49cde41a7 make style 2023-03-30 12:09:28 -04:00
MKhalusova e4dcfaf1b3 task guide based on notebook 2023-03-30 11:30:55 -04:00
Younes BelkadaSourab Mangrulkaredbeeching
 		8f63f565c6 [utils] add merge_lora utility function (#227) 
* add merge_lora utility function

* forward contrib credits from original script

* some changes

* make style

* fix tets

* finally fix tests

* Update tests/test_peft_model.py

* adapt from suggestions

* adapt

* Update src/peft/tuners/lora.py

Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com>

* fix 8bit

* Update src/peft/tuners/lora.py

Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com>

---------

Co-authored-by: edbeeching <edbeeching@users.noreply.github.com>
Co-authored-by: Sourab Mangrulkar <13534540+pacman100@users.noreply.github.com>
 2023-03-30 13:45:37 +02:00
Sourab Mangrulkar 542f2470e7 Merge pull request #214 from huggingface/smangrul/add-docs 
add docs
 2023-03-30 11:10:14 +05:30
Sourab Mangrulkar 98f51e0876 Merge branch 'main' into smangrul/add-docs 2023-03-30 10:46:37 +05:30
Sourab Mangrulkar c7b5280d3c Merge pull request #231 from aitor-gamarra/main 
Show CONFIG_NAME instead of "config.json"
 2023-03-30 10:29:05 +05:30
Aitor Gamarra d6c68ae1a5 Show CONFIG_NAME instead of "config.json" 2023-03-29 21:03:39 +02:00
Younes Belkada df71b84341 [CI] Add more ci tests (#223) 
* add more tests

* fix

* add generate tests

* make style

* fix test

* add -n

* skip llama
 2023-03-29 15:28:38 +02:00
Vineet KumarYounes BelkadaVineet Kumar
 		d8d1007732 Causal LM generation fix for prefix tuning: GPT2 model (#222) 
* expand attention mask after preparing generation inputs for prefix tuning

* reformat

* Update src/peft/peft_model.py

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* reformat as per black

---------

Co-authored-by: Vineet Kumar <vineeku6@in.ibm.com>
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
 2023-03-29 15:20:14 +02:00
Sourab Mangrulkar 51f49a5fe4 Merge pull request #224 from younesbelkada/fix-ci-dreambooth 
Fix failing test on `main`
 2023-03-29 17:15:42 +05:30
Sourab Mangrulkar 4626b36e27 addressing remaining comments 2023-03-29 17:12:32 +05:30
younesbelkada 891584c8d9 fix ci dreambooth 2023-03-28 13:55:43 +00:00
Sourab MangrulkarandSteven Liu 13476a807c Apply suggestions from code review 
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-03-27 13:44:00 +05:30
Sourab Mangrulkar 3d00af4799 add docs 2023-03-24 13:16:26 +05:30
Sourab Mangrulkar 098962fa65 Merge pull request #204 from haofanwang/patch-1 
Update train_dreambooth.py
 2023-03-24 10:29:09 +05:30
Younes Belkada d8c3b6bca4 Fix CI tests (#210) 
* fix ci ruuner creation

* fix python versions

* fix setup and test
 2023-03-23 12:54:52 +01:00
Younes Belkada 2632e7eba7 [CI] Add ci tests (#203) 
* add ci tests

* fix some tests

* fix tests

* rename

* fix

* update tests

* try

* temp hotfix

* refactor tests

* Update .github/workflows/tests.yml

* fix test
 2023-03-23 12:38:40 +01:00
Haofan Wang b5b3ae3cbe Update train_dreambooth.py 2023-03-21 21:38:15 +08:00
Sourab Mangrulkar 13e53fc7ee Merge pull request #180 from mymusise/chatglm 
ChatGLM support
 2023-03-20 15:02:58 +05:30
mymusise 54b6ce2c0e ChatGLM support 
Signed-off-by: mymusise <mymusise1@gmail.com>
 2023-03-16 19:09:12 +08:00
Sourab Mangrulkar 64f63a7df2 Merge pull request #167 from dumpmemory/update-readme-patch-for-zero-init 
Update README.md
 2023-03-15 22:33:42 +05:30
Younes Belkada df0e1fb592 [core] Fix peft multi-gpu issue (#145) 
* add multi-gpu support

* rm deepcopy

* tryo to comment

* style

* fix nits
 2023-03-14 13:06:33 +01:00
Sourab Mangrulkar 1c11bc067f Merge pull request #160 from zphang/llama 
Support for LLaMA models
 2023-03-14 11:18:29 +05:30
Sourab Mangrulkar 3b3fc47f84 Merge pull request #170 from PanQiWei/temporarily_replace_prepare_inputs_for_generation 
Replace base_model's function temporarily
 2023-03-14 11:05:01 +05:30
Sourab Mangrulkar 321cbd6829 Merge pull request #172 from huggingface/smangrul/fix-megred-linear-lora-issues 
fixing merged_linear lora issues
 2023-03-14 10:56:44 +05:30
Sourab Mangrulkar 43cb7040c6 fixing merged_linear lora issues 2023-03-13 16:01:28 +05:30
PanQiWei 644d68ee6f changed: 1. replace base_model.prepare_inputs_for_generation and base_model._prepare_encoder_decoder_kwargs_for_generation temporarily 2023-03-10 10:36:11 +08:00
dumpmemory 354bea8719 Update README.md 2023-03-09 22:03:40 +08:00
dumpmemory e85c18f019 Update README.md 
add one caveat situation for using LoRA + ZeRO 3 setting.
 2023-03-09 22:01:16 +08:00
Sourab Mangrulkar 50aaf99da7 Merge pull request #166 from huggingface/smangrul/release-v0.3.0.dev0 
release v0.3.0.dev0
 2023-03-09 09:24:05 +05:30
Sourab Mangrulkar 80c96de277 release v0.3.0.dev0 2023-03-09 09:23:24 +05:30
Sourab Mangrulkar eb07373477 Merge pull request #165 from huggingface/smangrul/add-trl-example-in-readme 
minor changes
 2023-03-09 08:58:09 +05:30
Sourab Mangrulkar f1980e9be2 minor changes 2023-03-09 08:57:52 +05:30
Sourab Mangrulkar 8777b5606d Merge pull request #164 from huggingface/smangrul/add-trl-example-in-readme 
Update README.md
 2023-03-09 08:53:56 +05:30
Sourab Mangrulkar 4497d6438c Update README.md 2023-03-09 08:53:36 +05:30
Sourab Mangrulkar 3d898adb26 Merge pull request #157 from huggingface/smangrul/lora_fixes_and_updates_wrt_trl 
lora fixes and adding 8bitMegredLinear lora
 2023-03-08 23:06:25 +05:30
Sourab Mangrulkar 842b09a280 Merge pull request #159 from zphang/prefix_citation 
Add Prefix Tuning citation
 2023-03-08 23:05:17 +05:30
Sourab Mangrulkar 91c69a80ab Merge pull request #162 from dumpmemory/fix_count 
fix count
 2023-03-08 23:03:58 +05:30
Sourab Mangrulkar c1199931de Merge pull request #163 from alvanli/alvanli/add-local-saving-whisper-largev2 
Add local saving for whisper largev2 example notebook
 2023-03-08 23:02:36 +05:30
alvanli 5e788b329d Use on save callback 2023-03-08 10:05:53 -05:00
alvanli 48dc4c624e Add callback to save to local 2023-03-08 09:57:13 -05:00
dumpmemory d2b99c0b62 fix count 
num_params should be directly used.
 2023-03-08 18:41:30 +08:00
Jason Phang baa2a4d53f LLaMA support 2023-03-07 21:05:58 -05:00
Jason Phang 27c2701555 Add Prefix Tuning citation 2023-03-07 19:17:35 -05:00
Sourab Mangrulkar a43ef6ec72 fixing ds conv1D issue thanks to @dumpmemory 2023-03-08 00:53:08 +05:30
Sourab Mangrulkar c81b6680e7 adding 8bitMegredLinear lora 2023-03-07 17:59:02 +05:30
Sourab Mangrulkar 8358b27445 Merge pull request #149 from huggingface/smangrul/fixes 
minor fixes to the examples
 2023-03-07 14:08:25 +05:30
Sourab Mangrulkar b9451ab458 fixing issues and quality ✨ 2023-03-07 14:04:19 +05:30
Sourab Mangrulkar ce4e6f3dd9 Merge pull request #150 from mayank31398/mayank/single-module 
support option for encoder only prompts
 2023-03-04 09:03:26 +05:30
mayank31398 53eb209387 support option for encoder only prompts 2023-03-03 23:43:25 +05:30