Younes Belkada ae9a344cce [Mistral] Add Flash Attention-2 support for mistral (#26464) ...

* add FA-2 support for mistral

* fixup

* add sliding windows

* fixing few nits

* v1 slicing cache - logits do not match

* add comment

* fix bugs

* more mem efficient

* add warning once

* add warning once

* oops

* fixup

* more comments

* copy

* add safety checker

* fixup

* Update src/transformers/models/mistral/modeling_mistral.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* copied from

* up

* raise when padding side is right

* fixup

* add doc + few minor changes

* fixup

---------

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

2023-10-03 13:44:46 +02:00

..

internal

Generate: add missing logits processors docs (#25653)

2023-08-25 11:56:17 +01:00

main_classes

Add image to image pipeline (#25393)

2023-09-22 19:53:55 +03:00

model_doc

[Mistral] Add Flash Attention-2 support for mistral (#26464)

2023-10-03 13:44:46 +02:00

tasks

[Mistral] Mistral-7B-v0.1 support (#26447)

2023-09-27 18:30:46 +02:00

_config.py

Enable doc in Spanish (#16518)

2022-04-04 10:25:46 -04:00

_toctree.yml

[Mistral] Mistral-7B-v0.1 support (#26447)

2023-09-27 18:30:46 +02:00

accelerate.md

Fix typos (#25936)

2023-09-04 11:15:12 +01:00

add_new_model.md

Update add_new_model.md (#26365)

2023-09-25 12:58:11 +02:00

add_new_pipeline.md

Update add_new_pipeline.md (#26197)

2023-09-19 00:41:16 +02:00

add_tensorflow_model.md

Remove utils/documentation_tests.txt (#26213)

2023-09-18 13:33:01 +02:00

attention.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

autoclass_tutorial.md

Update autoclass_tutorial.md (#25929)

2023-09-04 11:16:49 +01:00

benchmarks.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

bertology.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

big_models.md

Fix typos (#25936)

2023-09-04 11:15:12 +01:00

chat_templating.md

Tweaks to Chat Templates docs (#26168)

2023-09-15 12:50:57 +01:00

community.md

Update community.md (#25928)

2023-09-04 11:16:34 +01:00

contributing.md

Enable doc in Spanish (#16518)

2022-04-04 10:25:46 -04:00

create_a_model.md

Fix typos (#25936)

2023-09-04 11:15:12 +01:00

custom_models.md

Fix typos (#25936)

2023-09-04 11:15:12 +01:00

custom_tools.md

[doc] Always call it Agents for consistency (#25958)

2023-09-05 12:27:20 +01:00

debugging.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

fast_tokenizers.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

generation_strategies.md

[docs] navigation improvement between text gen pipelines and text gen params (#26477)

2023-09-29 09:43:39 +02:00

glossary.md

Fix typos (#25936)

2023-09-04 11:15:12 +01:00

hpo_train.md

enable optuna multi-objectives feature (#25969)

2023-09-12 18:01:22 +01:00

index.md

[Mistral] Mistral-7B-v0.1 support (#26447)

2023-09-27 18:30:46 +02:00

installation.md

[docs] Update offline mode docs (#26478)

2023-09-29 09:42:21 +02:00

llm_tutorial.md

Fix typos (#25936)

2023-09-04 11:15:12 +01:00

model_memory_anatomy.md

Fix typos (#25936)

2023-09-04 11:15:12 +01:00

model_sharing.md

Fix typos (#25936)

2023-09-04 11:15:12 +01:00

model_summary.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

multilingual.md

Fix typo in example code (#25583)

2023-08-18 07:58:59 +02:00

notebooks.md

Enable doc in Spanish (#16518)

2022-04-04 10:25:46 -04:00

pad_truncation.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

peft.md

[PEFT] Peft integration alternative design (#25077)

2023-08-18 19:08:03 +02:00

perf_hardware.md

🌐 [i18n-KO] Translated perf_hardware.md to Korean (#24966)

2023-07-25 07:44:24 -04:00

perf_infer_cpu.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

perf_infer_gpu_many.md

[core ] Integrate Flash attention 2 in most used models (#25598)

2023-09-22 17:42:10 +02:00

perf_infer_gpu_one.md

[Mistral] Add Flash Attention-2 support for mistral (#26464)

2023-10-03 13:44:46 +02:00

perf_infer_special.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

perf_torch_compile.md

Fix rendering for torch.compile() docs (#25432)

2023-08-10 13:25:00 +02:00

perf_train_cpu_many.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

perf_train_cpu.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

perf_train_gpu_many.md

deprecate sharded_ddp training argument (#24825)

2023-07-17 06:57:42 -04:00

perf_train_gpu_one.md

[core ] Integrate Flash attention 2 in most used models (#25598)

2023-09-22 17:42:10 +02:00

perf_train_special.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

perf_train_tpu_tf.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

perf_train_tpu.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

performance.md

[docs] Performance docs tidy up, part 1 (#23963)

2023-07-24 08:57:24 -04:00

perplexity.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

philosophy.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

pipeline_tutorial.md

[ASR Pipe] Improve docs and error messages (#26476)

2023-09-29 18:32:37 +01:00

pipeline_webserver.md

Suggestions on Pipeline_webserver (#25570)

2023-08-18 10:17:44 +02:00

pr_checks.md

Document check copies (#25291)

2023-08-04 14:56:29 +02:00

preprocessing.md

Removal of deprecated vision methods and specify deprecation versions (#24570)

2023-06-29 15:09:51 +01:00

quicktour.md

[TYPO] fix typo/format in quicktour.md (#25519)

2023-08-16 08:03:23 +02:00

run_scripts.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

sagemaker.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

serialization.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

task_summary.md

Fix doctest (#25031)

2023-07-25 22:10:06 +02:00

tasks_explained.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

testing.md

fix wrong path in some doc (#25658)

2023-08-23 08:34:30 +02:00

tf_xla.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

tflite.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

tokenizer_summary.md

Fix typo: Roberta -> RoBERTa (#25302)

2023-08-03 14:17:30 -07:00

torchscript.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

training.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

transformers_agents.md

[doc] Always call it Agents for consistency (#25958)

2023-09-05 12:27:20 +01:00

troubleshooting.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00