Jason Phang 0041be5b3d LLaMA Implementation (#21955) ...

* 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: Stella Biderman <stellabiderman@gmail.com>

2023-03-16 09:00:53 -04:00

..

benchmark

[Test refactor 1/5] Per-folder tests reorganization (#15725)

2022-02-23 15:46:28 -05:00

deepspeed

[deepspeed] offload + non-cpuadam optimizer exception (#22043)

2023-03-09 08:12:57 -08:00

extended

Apply ruff flake8-comprehensions (#21694)

2023-02-22 09:14:54 +01:00

fixtures

[WIP] add SpeechT5 model (#18922)

2023-02-03 12:43:46 -05:00

generation

Remove set_access_token usage + fail tests if FutureWarning (#22051)

2023-03-09 09:23:48 -05:00

mixed_int8

[bnb] fix bnb decoders bug (#21688)

2023-02-20 12:21:58 +00:00

models

LLaMA Implementation (#21955)

2023-03-16 09:00:53 -04:00

onnx

Update quality tooling for formatting (#21480)

2023-02-06 18:10:56 -05:00

optimization

Make schedulers picklable by making lr_lambda fns global (#21768)

2023-03-02 12:08:43 -05:00

pipelines

Regression pipeline device (#22190)

2023-03-15 14:13:38 -04:00

repo_utils

Add an utility file to get information from test files (#21856)

2023-03-01 17:53:29 +01:00

sagemaker

Apply ruff flake8-comprehensions (#21694)

2023-02-22 09:14:54 +01:00

tokenization

Update quality tooling for formatting (#21480)

2023-02-06 18:10:56 -05:00

trainer

handle numpy inputs in whole word mask data collator (#22032)

2023-03-10 10:50:29 -05:00

utils

Add Blip and Blip2 for pipeline tests (#21904)

2023-03-02 18:20:34 +01:00

__init__.py

GPU text generation: mMoved the encoded_prompt to correct device

2020-01-06 15:11:12 +01:00

test_configuration_common.py

Remove set_access_token usage + fail tests if FutureWarning (#22051)

2023-03-09 09:23:48 -05:00

test_feature_extraction_common.py

Remove set_access_token usage + fail tests if FutureWarning (#22051)

2023-03-09 09:23:48 -05:00

test_image_processing_common.py

Remove set_access_token usage + fail tests if FutureWarning (#22051)

2023-03-09 09:23:48 -05:00

test_image_transforms.py

to_pil - don't rescale if int and in range 0-255 (#22158)

2023-03-14 15:43:44 +00:00

test_modeling_common.py

[Safetensors] Add explicit flag to from pretrained (#22083)

2023-03-13 21:39:06 +01:00

test_modeling_flax_common.py

Remove set_access_token usage + fail tests if FutureWarning (#22051)

2023-03-09 09:23:48 -05:00

test_modeling_tf_common.py

Remove set_access_token usage + fail tests if FutureWarning (#22051)

2023-03-09 09:23:48 -05:00

test_pipeline_mixin.py

Move is_pipeline_test_to_skip to specific model test classes (#21999)

2023-03-14 10:03:02 +01:00

test_sequence_feature_extraction_common.py

Apply ruff flake8-comprehensions (#21694)

2023-02-22 09:14:54 +01:00

test_tokenization_common.py

Remove set_access_token usage + fail tests if FutureWarning (#22051)

2023-03-09 09:23:48 -05:00