Commit Graph

13 Commits

Author SHA1 Message Date
Yanan Xie
b09912c8f4
Fix mistral generate for long prompt / response (#27548)
* Fix mistral generate for long prompt / response

* Add unit test

* fix linter

* fix linter

* fix test

* add assisted generation test for mistral and load the model in 4 bit + fa2
2023-11-27 10:18:41 +01:00
Yih-Dar
623432dcc9
Skip pipeline tests for 2 models for now (#27687)
fix

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
2023-11-24 09:43:20 +01:00
fxmarty
7f04373865
Explicitely specify use_cache=True in Flash Attention tests (#27635)
explicit use_cache=True
2023-11-22 01:53:10 +09:00
fxmarty
82cc0a79ac
Fix flash attention bugs with Mistral and Falcon (#27625)
* fix various bugs with flash attention

* bump

* fix test

* fix mistral

* use skiptest instead of return that may be misleading

* fix on review
2023-11-21 23:20:44 +09:00
Arthur
651408a077
[Styling] stylify using ruff (#27144)
* try to stylify using ruff

* might need to remove these changes?

* use ruf format andruff check

* use isinstance instead of type comparision

* use # fmt: skip

* use # fmt: skip

* nits

* soem styling changes

* update ci job

* nits isinstance

* more files update

* nits

* more nits

* small nits

* check and format

* revert wrong changes

* actually use formatter instead of checker

* nits

* well docbuilder is overwriting this commit

* revert notebook changes

* try to nuke docbuilder

* style

* fix feature exrtaction test

* remve `indent-width = 4`

* fixup

* more nits

* update the ruff version that we use

* style

* nuke docbuilder styling

* leve the print for detected changes

* nits

* Remove file I/O

Co-authored-by: charliermarsh
 <charlie.r.marsh@gmail.com>

* style

* nits

* revert notebook changes

* Add # fmt skip when possible

* Add # fmt skip when possible

* Fix

* More `  # fmt: skip` usage

* More `  # fmt: skip` usage

* More `  # fmt: skip` usage

* NIts

* more fixes

* fix tapas

* Another way to skip

* Recommended way

* Fix two more fiels

* Remove asynch
Remove asynch

---------

Co-authored-by: charliermarsh <charlie.r.marsh@gmail.com>
2023-11-16 17:43:19 +01:00
Yih-Dar
3258ff9330
use pytest.mark directly (#27390)
fix

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
2023-11-09 13:32:54 +01:00
Hz, Ji
50378cbf6c
device agnostic models testing (#27146)
* device agnostic models testing

* add decorator `require_torch_fp16`

* make style

* apply review suggestion

* Oops, the fp16 decorator was misused
2023-10-31 18:12:14 +01:00
Yih-Dar
b8f1cde931
Fix Mistral OOM again (#26847)
fix

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
2023-10-16 22:47:20 +02:00
Yih-Dar
db5e0c3292
Fix MistralIntegrationTest OOM (#26754)
* fix

* fix

* fix

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
2023-10-12 12:31:11 +02:00
Yih-Dar
5334796d20
Copied from for test files (#26713)
* copied statement for test files

---------

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
2023-10-11 14:12:09 +02:00
fxmarty
64845307b3
Remove unnecessary unsqueeze - squeeze in rotary positional embedding (#26162)
* remove unnecessary unsqueeze-squeeze in llama

* correct other models

* fix

* revert gpt_neox_japanese

* fix copie

* fix test
2023-10-06 18:25:15 +09:00
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
Chris Bamford
72958fcd3c
[Mistral] Mistral-7B-v0.1 support (#26447)
* [Mistral] Mistral-7B-v0.1 support

* fixing names

* slightly longer test

* fixups

* not_doctested

* wrongly formatted references

* make fixuped

---------

Co-authored-by: Timothee Lacroix <t@eugen.ai>
Co-authored-by: timlacroix <t@mistral.ai>
2023-09-27 18:30:46 +02:00