Hamel Husain
8b12468230
Add QLoRA + FSDP Docs ( #1403 )
...
* pre commit
* Update fsdp_qlora.md
2024-03-14 11:04:51 -04:00
Hamel Husain
ed70a08348
add docs for input_output format ( #1367 ) [skip ci]
...
* add docs
* add docs
* run linter
2024-03-06 09:09:49 -05:00
Hamel Husain
5265cd6b2c
Update debugging.md ( #1339 ) [skip ci]
2024-02-27 15:47:31 +09:00
Maxime
0f6af36d50
Mps mistral lora ( #1292 ) [skip ci]
...
* Lora example for Mistral on MPS backend
* Add some MPS documentation
* Update examples/mistral/lora-mps.yml
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com >
* Update examples/mistral/lora-mps.yml
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com >
* Update README.md
---------
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com >
Co-authored-by: Wing Lian <wing.lian@gmail.com >
2024-02-26 22:39:57 -05:00
Wing Lian
00568c1539
support for true batches with multipack ( #1230 )
...
* support for true batches with multipack
* patch the map dataset fetcher to handle batches with packed indexes
* patch 4d mask creation for sdp attention
* better handling for BetterTransformer
* patch general case for 4d mask
* setup forward patch. WIP
* fix patch file
* support for multipack w/o flash attention for llama
* cleanup
* add warning about bf16 vs fp16 for multipack with sdpa
* bugfixes
* add 4d multipack tests, refactor patches
* update tests and add warnings
* fix e2e file check
* skip sdpa test if not at least torch 2.1.1, update docs
2024-02-01 10:18:42 -05:00
Hamel Husain
52c83d30bf
Update rlhf.md ( #1237 ) [skip ci]
2024-01-31 17:27:35 -05:00
Wing Lian
5bce45f800
more dpo fixes for dataset loading and docs ( #1185 ) [skip ci]
...
* more dpo fixes for dataset loading and docs
* preprocess dpo datasets
2024-01-24 14:23:55 -05:00
Aleksey Korshuk
dc051b861d
Update rlhf.md ( #1178 ) [skip ci]
2024-01-23 15:54:51 -05:00
Hamel Husain
304ea1b814
Update debugging.md ( #1111 )
2024-01-12 21:07:31 -08:00
Hamel Husain
2dc431078c
Add link on README to Docker Debugging ( #1107 )
...
* add docker debug
* Update docs/debugging.md
Co-authored-by: Wing Lian <wing.lian@gmail.com >
* explain editable install
* explain editable install
* upload new video
* add link to README
* Update README.md
* Update README.md
* chore: lint
* make sure to lint markdown too
---------
Co-authored-by: Wing Lian <wing.lian@gmail.com >
2024-01-12 08:51:35 -05:00
Hamel Husain
6d342b52a4
Add section for debugging with Docker ( #1104 )
...
* add docker debug
* Update docs/debugging.md
Co-authored-by: Wing Lian <wing.lian@gmail.com >
* explain editable install
* explain editable install
* upload new video
---------
Co-authored-by: Wing Lian <wing.lian@gmail.com >
2024-01-11 18:43:33 -08:00
NanoCode012
b432889256
feat: enable trl's autounwrap ( #1060 )
...
* feat: test trl's autounwrap
* fix: add check for adapter
* feat: add config to disable autounwrap
* chore: fix lint
2024-01-11 08:43:41 -05:00
Hamel Husain
54fe07a905
Fix debugging.md ( #1091 )
2024-01-10 21:44:40 -08:00
Hamel Husain
7512c3ad20
Add Debugging Guide ( #1089 )
...
* add debug guide
* add background
* add .gitignore
* Update devtools/dev_sharegpt.yml
Co-authored-by: Wing Lian <wing.lian@gmail.com >
* Update docs/debugging.md
Co-authored-by: Wing Lian <wing.lian@gmail.com >
* simplify example axolotl config
* add additional comments
* add video and TOC
* try jsonc for better md rendering
* style video thumbnail better
* fix footnote
---------
Co-authored-by: Wing Lian <wing.lian@gmail.com >
2024-01-10 20:49:24 -08:00
Wing Lian
f243c2186d
RL/DPO ( #935 )
...
* ipo-dpo trainer
* fix missing abstract method
* chatml template, grad checkpointing kwargs support
* fix steps calc for RL and add dataloader kwargs
* wip to fix dpo and start ppo
* more fixes
* refactor to generalize map fn
* fix dataset loop and handle argilla pref dataset
* set training args
* load reference model on seperate gpu if more than one device
* no auto upload to hub for dpo, don't add lora adapters to ref model for dpo
* fixes for rl training
* support for ipo from yaml
* set dpo training args from the config, add tests
* chore: lint
* set sequence_len for model in test
* add RLHF docs
2024-01-04 18:22:55 -05:00
NanoCode012
9f7e8a971d
feat(doc): add dummyoptim faq fix ( #802 )
2023-10-29 23:06:06 +09:00
Wing Lian
a21935f07a
add to docs ( #703 )
2023-10-19 21:32:30 -04:00
Wing Lian
2aa1f71464
fix pytorch 2.1.0 build, add multipack docs ( #722 )
2023-10-13 08:57:28 -04:00
Maxime
c1382e79b6
Create multi-node.md ( #613 )
...
* Create multi-node.md
* Update multi-node.md
* Update multi-node.md
2023-09-20 22:02:16 -04:00
The Objective Dad
5e2d8a42d9
Adding NCCL Timeout Guide ( #536 )
...
* fixes NCCL_P2P_LEVEL=NVL #429
* adding more insights into verious values of NCCL_P2P_LEVEL
2023-09-08 11:57:47 -04:00
