Poedator
d78e78a0e4
HfQuantizer class for quantization-related stuff in modeling_utils.py (#26610 )
...
* squashed earlier commits for easier rebase
* rm rebase leftovers
* 4bit save enabled @quantizers
* TMP gptq test use exllama
* fix AwqConfigTest::test_wrong_backend for A100
* quantizers AWQ fixes
* _load_pretrained_model low_cpu_mem_usage branch
* quantizers style
* remove require_low_cpu_mem_usage attr
* rm dtype arg from process_model_before_weight_loading
* rm config_origin from Q-config
* rm inspect from q_config
* fixed docstrings in QuantizationConfigParser
* logger.warning fix
* mv is_loaded_in_4(8)bit to BnbHFQuantizer
* is_accelerate_available error msg fix in quantizer
* split is_model_trainable in bnb quantizer class
* rm llm_int8_skip_modules as separate var in Q
* Q rm todo
* fwd ref to HFQuantizer in type hint
* rm note re optimum.gptq.GPTQQuantizer
* quantization_config in __init__ simplified
* replaced NonImplemented with create_quantized_param
* rm load_in_4/8_bit deprecation warning
* QuantizationConfigParser refactoring
* awq-related minor changes
* awq-related changes
* awq config.modules_to_not_convert
* raise error if no q-method in q-config in args
* minor cleanup
* awq quantizer docstring
* combine common parts in bnb process_model_before_weight_loading
* revert test_gptq
* .process_model_ cleanup
* restore dict config warning
* removed typevars in quantizers.py
* cleanup post-rebase 16 jan
* QuantizationConfigParser classmethod refactor
* rework of handling of unexpected aux elements of bnb weights
* moved q-related stuff from save_pretrained to quantizers
* refactor v1
* more changes
* fix some tests
* remove it from main init
* ooops
* Apply suggestions from code review
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
* fix awq issues
* fix
* fix
* fix
* fix
* fix
* fix
* add docs
* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* Apply suggestions from code review
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* Update docs/source/en/hf_quantizer.md
* address comments
* fix
* fixup
* Update src/transformers/modeling_utils.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* Update src/transformers/modeling_utils.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* address final comment
* update
* Update src/transformers/quantizers/base.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* Update src/transformers/quantizers/auto.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* fix
* add kwargs update
* fixup
* add `optimum_quantizer` attribute
* oops
* rm unneeded file
* fix doctests
---------
Co-authored-by: younesbelkada <younesbelkada@gmail.com>
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
2024-01-30 02:48:25 +01:00
Omar Sanseviero
a989c6c6eb
Don't allow passing load_in_8bit and load_in_4bit at the same time ( #28266 )
...
* Update quantization_config.py
* Style
* Protect from setting directly
* add tests
* Update tests/quantization/bnb/test_4bit.py
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
---------
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
2024-01-30 01:43:40 +01:00
Marc Sun
7c8dd88d13
[GPTQ] Fix test ( #28018 )
...
* fix test
* reduce length
* smaller model
2024-01-15 11:22:54 -05:00
Younes Belkada
266c67b06a
[Mixtral / Awq] Add mixtral fused modules for Awq ( #28240 )
...
* add mixtral fused modules
* add changes from modeling utils
* add test
* fix test + rope theta issue
* Update src/transformers/modeling_utils.py
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
* add tests
---------
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2024-01-12 14:29:35 +01:00
Younes Belkada
07bdbebb48
[Awq] Add llava fused modules support ( #28239 )
...
* add llava + fused modules
* Update src/transformers/models/llava/modeling_llava.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
---------
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
2024-01-12 06:55:54 +01:00
Younes Belkada
fa21ead73d
[Awq] Enable the possibility to skip quantization for some target modules ( #27950 )
...
* v1
* add docstring
* add tests
* add awq 0.1.8
* oops
* fix test
2023-12-25 11:06:56 +01:00
Poedator
4f7806ef7e
[bnb] Let's make serialization of 4bit models possible ( #26037 )
...
* updated bitsandbytes.py
* rm test_raise_* from test_4bit.py
* add test_4bit_serialization.py
* modeling_utils bulk edits
* bnb_ver 0.41.3 in integrations/bitsandbytes.py
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* @slow reinstated
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* bnb ver 0.41.3 in src/transformers/modeling_utils.py
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* rm bnb version todo in integrations/bitsandbytes.py
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* moved 4b serialization tests to test_4bit
* tests upd for opt
* to torch_device
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* ruff fixes to tests
* rm redundant bnb version check in mod_utils
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* restore _hf_peft_config_loaded modeling_utils.py::2188
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* restore _hf_peft_config_loaded test in modeling_utils.py::2199
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* fixed NOT getattr(self, "is_8bit_serializable")
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* setting model.is_4bit_serializable
* rm separate fp16_statistics arg from set_module...
* rm else branch in integrations::bnb::set_module
* bnb 4bit dtype check
* upd comment on 4bit weights
* upd tests for FP4 safe
---------
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
2023-12-21 11:54:44 +01:00
Younes Belkada
fdb85be40f
Faster generation using AWQ + Fused modules ( #27411 )
...
* v1 fusing modules
* add fused mlp support
* up
* fix CI
* block save_pretrained
* fixup
* small fix
* add new condition
* add v1 docs
* add some comments
* style
* fix nit
* adapt from suggestion
* add check
* change arg names
* change variables name
* Update src/transformers/integrations/awq.py
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
* style
* split up into 3 different private methods
* more conditions
* more checks
* add fused tests for custom models
* fix
* fix tests
* final update docs
* final fixes
* fix importlib metadata
* Update src/transformers/utils/quantization_config.py
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
* change it to `do_fuse`
* nit
* Update src/transformers/utils/quantization_config.py
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
* Update src/transformers/utils/quantization_config.py
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
* Update src/transformers/utils/quantization_config.py
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
* few fixes
* revert
* fix test
* fix copies
* raise error if model is not quantized
* add test
* use quantization_config.config when fusing
* Update src/transformers/modeling_utils.py
---------
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
2023-12-05 12:14:45 +01:00
Younes Belkada
7b139023c3
[AWQ ] Addresses TODO for awq tests ( #27467 )
...
addresses todo for awq tests
2023-11-13 18:18:41 +01:00
Younes Belkada
fd685cfd59
[Quantization] Add str to enum conversion for AWQ ( #27320 )
...
* add str to enum conversion
* fixup
* Apply suggestions from code review
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
---------
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2023-11-10 13:45:00 +01:00
Younes Belkada
9b25c164bd
[core / Quantization] Fix for 8bit serialization tests ( #27234 )
...
* fix for 8bit serialization
* added regression tests.
* fixup
2023-11-02 12:03:51 +01:00
Marc Sun
c9e72f55b2
Add exllamav2 better ( #27111 )
...
* add_ xllamav2 arg
* add test
* style
* add check
* add doc
* replace by use_exllama_v2
* fix tests
* fix doc
* style
* better condition
* fix logic
* add deprecate msg
* deprecate exllama
* remove disable_exllama from the linter
* remove
* fix warning
* Revert the commits deprecating exllama
* deprecate disable_exllama for use_exllama
* fix
* fix loading attribute
* better handling of args
* remove disable_exllama from init and linter
* Apply suggestions from code review
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
* better arg
* fix warning
* Apply suggestions from code review
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
* switch to dict
* Apply suggestions from code review
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
* style
* nits
* style
* better tests
* style
---------
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2023-11-01 13:09:21 -04:00
Younes Belkada
ae093eef01
[core / Quantization ] AWQ integration ( #27045 )
...
* working v1
* oops
* Update src/transformers/modeling_utils.py
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
* fixup
* oops
* push
* more changes
* add docs
* some fixes
* fix copies
* add v1 doc
* added installation guide
* relax constraints
* revert
* attempt llm-awq
* oops
* oops
* fixup
* raise error when incorrect cuda compute capability
* nit
* add instructions for llm-awq
* fixup
* fix copies
* fixup and docs
* change
* few changes + add demo
* add v1 tests
* add autoawq in dockerfile
* finalize
* Update tests/quantization/autoawq/test_awq.py
* fix test
* fix
* fix issue
* Update src/transformers/integrations/awq.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* Update docs/source/en/main_classes/quantization.md
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* Update docs/source/en/main_classes/quantization.md
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* Update src/transformers/integrations/awq.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* Update src/transformers/integrations/awq.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* add link to example script
* Update docs/source/en/main_classes/quantization.md
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* add more content
* add more details
* add link to quantization docs
* camel case + change backend class name
* change to string
* fixup
* raise errors if libs not installed
* change to `bits` and `group_size`
* nit
* nit
* Apply suggestions from code review
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
* disable training
* address some comments and fix nits
* fix
* final nits and fix tests
* adapt to our new runners
* make fix-copies
* Update src/transformers/utils/quantization_config.py
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
* Update src/transformers/utils/quantization_config.py
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
* Update src/transformers/integrations/awq.py
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
* Update src/transformers/integrations/awq.py
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
* move to top
* add conversion test
* final nit
* add more elaborated test
---------
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2023-11-01 09:06:31 +01:00
Younes Belkada
4bb50aa212
[Quantization / tests ] Fix bnb MPT test ( #27178 )
...
fix bnb mpt test
2023-10-31 16:25:53 +01:00
Younes Belkada
6b466771b0
[tests / Quantization] Fix bnb test ( #27145 )
...
* fix bnb test
* link to GH issue
2023-10-30 15:43:08 +01:00
Arthur
90ee9cea19
Revert "add exllamav2 arg" ( #27102 )
...
Revert "add exllamav2 arg (#26437 )"
This reverts commit 8214d6e7b1
2023-10-27 11:23:06 +02:00
Marc Sun
8214d6e7b1
add exllamav2 arg ( #26437 )
...
* add_ xllamav2 arg
* add test
* style
* add check
* add doc
* replace by use_exllama_v2
* fix tests
* fix doc
* style
* better condition
* fix logic
* add deprecate msg
2023-10-26 10:15:05 -04:00
Younes Belkada
fd6a0ade9b
🚨 🚨 🚨 [Quantization] Store the original dtype in the config as a private attribute 🚨 🚨 🚨 ( #26761 )
...
* First step
* fix
* add adjustements for gptq
* change to `_pre_quantization_dtype`
* Update src/transformers/modeling_utils.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* fix serialization
* Apply suggestions from code review
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* fixup
---------
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
2023-10-16 19:56:53 +02:00
Heinz-Alexander Fuetterer
883ed4b344
chore: fix typos ( #26756 )
2023-10-12 18:00:27 +02:00
Younes Belkada
2aef9a9601
[PEFT] Final fixes ( #26559 )
...
* fix issues with PEFT
* logger warning futurewarning issues
* fixup
* adapt from suggestions
* oops
* rm test
2023-10-03 14:53:09 +02:00
Younes Belkada
6824461f2a
[core/ auto ] Fix bnb test with code revision + bug with code revision ( #26431 )
...
* fix bnb test with code revision
* fix test
* Apply suggestions from code review
* Update src/transformers/models/auto/auto_factory.py
* Update src/transformers/models/auto/auto_factory.py
* Update src/transformers/models/auto/auto_factory.py
2023-10-02 11:35:07 +02:00
Younes Belkada
7ccac73f74
[RWKV] Final fix RWMV 4bit ( #26134 )
...
* Final fix RWMV 4bit
* fixup
* add a test
* add more clarifications
2023-09-13 16:30:20 +02:00
Younes Belkada
c8b26096d4
[core] fix 4bit num_parameters ( #26132 )
...
* fix 4bit `num_parameters`
* stronger check
2023-09-13 14:12:35 +02:00
Marc Sun
fa6107c97e
modify context length for GPTQ + version bump ( #25899 )
...
* add new arg for gptq
* add tests
* add min version autogptq
* fix order
* skip test
* fix
* Update src/transformers/modeling_utils.py
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* fix style
* change model path
---------
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
2023-09-06 11:45:47 -04:00
Younes Belkada
4b79697865
🚨 🚨 🚨 [Refactor] Move third-party related utility files into integrations/ folder 🚨 🚨 🚨 ( #25599 )
...
* move deepspeed to `lib_integrations.deepspeed`
* more refactor
* oops
* fix slow tests
* Fix docs
* fix docs
* addess feedback
* address feedback
* final modifs for PEFT
* fixup
* ok now
* trigger CI
* trigger CI again
* Update docs/source/en/main_classes/deepspeed.md
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* import from `integrations`
* address feedback
* revert removal of `deepspeed` module
* revert removal of `deepspeed` module
* fix conflicts
* ooops
* oops
* add deprecation warning
* place it on the top
* put `FutureWarning`
* fix conflicts with not_doctested.txt
* add back `bitsandbytes` module with a depr warning
* fix
* fix
* fixup
* oops
* fix doctests
---------
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
2023-08-25 17:13:34 +02:00
Younes Belkada
584eeb5387
[AutoGPTQ] Add correct installation of GPTQ library + fix slow tests ( #25713 )
...
* add correct installation of GPTQ library
* update tests values
2023-08-24 14:57:16 +02:00
Younes Belkada
e7e9261a20
[Docs] Fix un-rendered images ( #25561 )
...
fix un-rendered images
2023-08-17 12:08:11 +02:00
Marc Sun
55db70c63d
GPTQ integration ( #25062 )
...
* GTPQ integration
* Add tests for gptq
* support for more quantization model
* fix style
* typo
* fix method
* Update src/transformers/modeling_utils.py
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* add dataclass and fix quantization_method
* fix doc
* Update tests/quantization/gptq/test_gptq.py
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* Apply suggestions from code review
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* modify dataclass
* add gtpqconfig import
* fix typo
* fix tests
* remove dataset as req arg
* remove tokenizer import
* add offload cpu quantization test
* fix check dataset
* modify dockerfile
* protect trainer
* style
* test for config
* add more log
* overwrite torch_dtype
* draft doc
* modify quantization_config docstring
* fix class name in docstring
* Apply suggestions from code review
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* more warning
* fix 8bit kwargs tests
* peft compatibility
* remove var
* fix is_gptq_quantized
* remove is_gptq_quantized
* fix wrap
* Update src/transformers/modeling_utils.py
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
* add exllama
* skip test
* overwrite float16
* style
* fix skip test
* Apply suggestions from code review
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* fix docsting formatting
* add doc
* better test
---------
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
2023-08-10 16:06:29 -04:00
