Skip to content

GitLab

Switch branch/tag
  1. 04 Apr, 2023 2 commits
  3. 03 Apr, 2023 3 commits
  5. 30 Mar, 2023 2 commits
  7. 28 Mar, 2023 1 commit
  9. 27 Mar, 2023 1 commit
    • Arthur's avatar
      [WIP]`NLLB-MoE` Adds the moe model (#22024) · 19ade242
      Arthur authored 
      * Initial commit

* update modeling code

* update doc

* add functions necessary

* fix impotrs

* revert changes

* fixup

* more styling to get going

* remove standalone encoder

* update code

* styling

* fix config and model

* update code and some refactoring

* make more tests pass

* Adding NLLB-200 - MoE - 54.5B for no language left behind
Fixes #21300

* fix mor common tests

* styke

* update testing file

* update

* update

* Router2 doc

* update check config with sparse layer

* add dummy router

* update current conversion script

* create on the fly conversion script

* Fixup

* style

* style 2

* fix empty return

* fix return

* Update default config sparse layers

* easier to create sparse layers

* update

* update conversion script

* update modeling

* add to toctree

* styling

* make ruff happy

* update docstring

* update conversion script

* update, will break tests but impelemting top2

* update

* ❗local groups are supported here

* ⚠️ Support for local groups is now removed ⚠️

This is because it has to work with model parallelism that we do not support

* finish simplificaiton

* Fix forward

* style

* fixup

* Update modelling and test, refactoring

* update tests

* remove final layer)norm as it is done in the FF

* routing works! Logits test added

* nit in test

* remove top1router

* style

* make sure sparse are tested. Had to change route_tokens a liottle bit

* add support for unslip models when converting

* fixup

* style

* update test s

* update test

* REFACTOR

* encoder outputs match!

* style

* update testing

* 🎉encoder and decoder logits match 🎉



* styleing

* update tests

* cleanup tests

* fix router test and CIs

* cleanup

* cleanup test styling

* fix tests

* Finally the generation tests match!

* cleanup

* update test

* style testing file

* remove script

* cleanup

* more cleanup

* nits

* update

* NLLB tokenizer is wrong and will be fixed soon

* use LongTensors

* update tests

* revert some small changes

* fix second expert sampling and batch prioritized routing

* update tests

* finish last tests

* make ruff happy

* update

* ruff again

* style

* Update docs/source/en/model_doc/nllb-moe.mdx
Co-authored-by: default avatarSylvain Gugger <35901082+sgugger@users.noreply.github.com>

* Updates based on review

* style and fix import issue

* nit

* more nits

* cleanup

* styling

* update test_seconde_expert_policy

* fix name

* last nit on the markdown examples

---------
Co-authored-by: default avatarSylvain Gugger <35901082+sgugger@users.noreply.github.com>
      19ade242
  11. 24 Mar, 2023 3 commits
    • Shubhamai's avatar
      Resnet flax (#21472) · a0cbbba3
      Shubhamai authored 
      

* [WIP] flax resnet

* added pretrained flax models, results reproducible

* Added pretrained flax models, results reproducible

* working on tests

* no real code change, just some comments

* [flax] adding support for batch norm layers

* fixing bugs related to pt+flax integration

* removing loss from modeling flax output class

* fixing classifier tests

* fixing comments, model output

* cleaning comments

* review changes

* review changes

* Apply suggestions from code review
Co-authored-by: default avataramyeroberts <22614925+amyeroberts@users.noreply.github.com>

* renaming Flax to PyTorch

---------
Co-authored-by: default avataramyeroberts <22614925+amyeroberts@users.noreply.github.com>
      a0cbbba3
    • Mitch Naylor's avatar
      Add Mega: Moving Average Equipped Gated Attention (#21766) · 57f25f4b
      Mitch Naylor authored 
      

* add mega file structure and plain pytorch version of mega source code

* added config class with old naming conventions

* filled in mega documentation

* added config class and embeddings with optional token types

* updated notes

* starting the conversion process, deleted intermediate and added use_cache back to config

* renamed config attributes in modeling_mega.py

* checkpointing before refactoring incremental decoding functions

* removed stateful incremental key/values for EMA and self-attention

* refactored MovingAverageGatedAttention to remove stateful k/v history and use unified attention mask

* MovingAverageGatedAttention works with incremental decoding + past values, added sequence length enforcement

* more comments in MovingAverageGatedAttention + checkpointing before GatedCrossAttention

* bug fix in attention mask handling in MovingAverageGatedAttention

* removed incremental state from GatedCrossAttention and removed IncrementalState class

* finished gated cross attention and got MegaLayer working

* fixed causal masking in mega decoder

* fixed how padding and causal masks are passed through MegaLayer with and without k/v caching

* finished MegaModel; tested with encoder, decoder-only, and cross-attention type inputs; started work on downstream classes; removed mentions of position_ids

* added optional dense hidden layer for masked and causal LM classes

* docstring updates in MultiHeadEMA and GatedCrossAttention, removed unnecessary inputs in cross-attention

* removed before_attn_fn in Mega class and updated docstrings and comments up to there

* bug fix in MovingAverageGatedAttention masking

* working conversion of MLM checkpoint in scratchpad script -- perfect matches

* moved arg for hidden dense layer in LM head to config; discovered issue where from_pretrained is renaming gamma and beta parameters

* renamed gamma and beta parameters to avoid HF renaming when loading from checkpoint

* finished checkpoint conversion script

* cleanup old class in mega config script

* removed 'copied from' statements and passing integration tests

* added num_attention_heads=1 to config for integration compatibility, decoder tests working, generation tests failing

* fixed tuple output of megamodel

* all common tests passing after fixing issues in decoder, gradient retention, and initialization

* added mega-specific tests, ready for more documentation and style checks

* updated docstrings; checkpoint before style fixes

* style and quality checks, fixed initialization problem in float_tensor, ready for PR

* added mega to toctree

* removed unnecessary arg in megaconfig

* removed unused arg and fixed code samples with leftover roberta models

* Apply suggestions from code review

Applied all suggestions except the one renaming a class, as I'll need to update that througout
Co-authored-by: default avatarArthur <48595927+ArthurZucker@users.noreply.github.com>

* fixed issue where .view breaks batch dimension, conversion script fixed with absolute imports, updated readme with Mega->MEGA

* removed asserts in Mega code, renamed sequencenorm, gatedcrossattention, and NFFN, replaced get_activation_fn with ACTFN, and added sequencenorm to layer norms

* reformatted .forward() docstrings to match style and removed unused mask input in cross-attention

* removed all reset_parameters() methods and rolled into MegaPreTrainedModel._init_weights()

* renamed all single-letter variables and improved readability in tensor size comments, Mega->MEGA in 2 documentation files

* variable names in NFFN

* manual Mega->MEGA changes in docs

* Mega->MEGA in config auto

* style and quality fixes

* Apply suggestions from code review
Co-authored-by: default avatarArthur <48595927+ArthurZucker@users.noreply.github.com>

* renamed parameters and variables with confusing names, added copied from statements, moved fft conv to its own method, other cleanup from PR comments

* commit before dealing with merge conflicts

* made new attention activation functions available in ACT2FN and added generation test from OPT

* style and quality in activations and tests

* documentation fixes, renaming variables in dropout and rotary positions, used built-in causal masking, encoders->layers in MegaModel, moved comments into docstrings

* style and quality fixes after latest updates, before rotary position ids

* causal mask in MegaBlock docstring + added missing device passing

* Apply suggestions from code review
Co-authored-by: default avatarArthur <48595927+ArthurZucker@users.noreply.github.com>

* Update README.md
Co-authored-by: default avatarSylvain Gugger <35901082+sgugger@users.noreply.github.com>

* added Mega prefixes where missing, reverted MegaSequenceNorm to if-else, other module renaming requested in PR

* style and quality fixes + readme updates pointing to main

---------
Co-authored-by: default avatarArthur <48595927+ArthurZucker@users.noreply.github.com>
Co-authored-by: default avatarSylvain Gugger <35901082+sgugger@users.noreply.github.com>
      57f25f4b
    • Ashwin Mathur's avatar
      Fix typo in Greedy Search Description (#22345) · b7960765
      Ashwin Mathur authored 
      Fix typo in greedy search docs
      b7960765
  13. 22 Mar, 2023 3 commits
  15. 20 Mar, 2023 3 commits
  17. 17 Mar, 2023 7 commits
  19. 16 Mar, 2023 2 commits
    • Jason Phang's avatar
      LLaMA Implementation (#21955) · 0041be5b
      Jason Phang authored 
      

* LLaMA

* sharding and docs

* tweak

* black

* inits

* ruff

* LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP

* init

* no checkpoint

* docs

* ruff

* type_vocab_size

* tokenizer fixes

* tokenizer fixes

* Update tokenization_llama.py

* Update tokenization_llama.py

* Update configuration_llama.py

* Update modeling_llama.py

* tokenizer add_bos by default

* licenses

* remove decoder

* norms and mlp

* rope overhaul

* tweaks

* black

* mention OPT implementation

* off-by-one naming

* typo

* fix

* tokenization fix and slicing bug

* padding config

* cleanup

* black

* update tests

* undo typo

* fix vocab caching logic

* ruff

* docbuilder

* attn fix from BlackSamorez

* initial feedback

* typo

* docs

* llama case

* llama case

* load checkpoint docs

* comment about tokenizer

* tokenizer defaults

* clear past_key_values if use_cache=False

* last tweaks

* last tweaks

* last tweaks

* last tweaks

---------
Co-authored-by: default avatarStella Biderman <stellabiderman@gmail.com>
      0041be5b
    • Alara Dirik's avatar
      Fix typo in Align docs (#22199) · 1485bd9c
      Alara Dirik authored 
      Fix align docs typo
      1485bd9c
  21. 14 Mar, 2023 2 commits
  23. 13 Mar, 2023 5 commits
  25. 10 Mar, 2023 2 commits
  27. 09 Mar, 2023 3 commits
  29. 08 Mar, 2023 1 commit