transformers
Run model as compressed/uncompressed mode
#34719
Merged

Run model as compressed/uncompressed mode #34719

horheynm
draft, run model as compreszed/uncompressed mode
caa9d6b3
draft
86a649d4
run run_compressed=False
b28d1d26
Merge branch 'main' into compressed-tensors/run_compressed
39afd396
Rocketknight1
run_compressed as attr
bbe0b424
Merge branch 'compressed-tensors/run_compressed' of github.com:neural…
99d2d8a3
SunMarc
SunMarc commented on 2024-11-20
set run_compressed=False using quantization_config
5bd706bb
remove redundant line
70aaee05
horheynm horheynm changed the title draft, run model as compreszed/uncompressed mode Run model as compressed/uncompressed mode 1 year ago
horheynm
make is_qat_trainable dependent on run_compressed status
32e693bb
add tests
4f06a789
horheynm horheynm marked this pull request as ready for review 1 year ago
Merge branch 'main' into compressed-tensors/run_compressed
edc64179
lint
668421b0
Merge branch 'compressed-tensors/run_compressed' of github.com:neural…
d5a8940f
full in docstring
d44e1c14
add decompress
42cf70df
horheynm
horheynm
horheynm commented on 2024-11-26
SunMarc
SunMarc commented on 2024-11-27
dsikka
dsikka commented on 2024-11-27
comments
068944ca
Merge branch 'main' into compressed-tensors/run_compressed
1cee2a21
decompress if model is compresssed and not run_compressed
0e6e339e
dsikka
dsikka commented on 2024-12-02
Merge branch 'main' into compressed-tensors/run_compressed
131225ba
apply_quant_config logic fix -- populate statedict properly
18371bc9
horheynm
horheynm
dsikka
dsikka commented on 2024-12-03
kylesayrs
kylesayrs requested changes on 2024-12-04
kylesayrs
kylesayrs requested changes on 2024-12-04
comments
2370ea6a
remove non compressed model
dac41d23
kylesayrs
kylesayrs commented on 2024-12-05
make is_compressed as property
01e9ca7a
SunMarc
SunMarc approved these changes on 2024-12-06
SunMarc SunMarc requested a review from ArthurZucker ArthurZucker 1 year ago
cosmetic
3599a270
Merge branch 'main' into compressed-tensors/run_compressed
4450e2d6
Merge branch 'main' into compressed-tensors/run_compressed
331832e1
horheynm
dsikka
dsikka commented on 2024-12-09
run apply_quant_config for non-compressed models -- popualte scales a…
4391525d
Merge branch 'compressed-tensors/run_compressed' of github.com:neural…
d267da10
add pahtway for decompressing sparse models
941af7e1
dsikka
dsikka commented on 2024-12-10
kylesayrs
kylesayrs approved these changes on 2024-12-10
typo on is_quantization_compressed
d3c418e9
dsikka
dsikka commented on 2024-12-10
Merge branch 'main' into compressed-tensors/run_compressed
3419e4ca
lint
3ca6adea
Merge branch 'compressed-tensors/run_compressed' of github.com:neural…
2e7ef0a8
horheynm
fix typo
d1d28e79
Merge branch 'main' into compressed-tensors/run_compressed
67599339
Merge branch 'main' into compressed-tensors/run_compressed
9d2f2ec5
HuggingFaceDocBuilderDev
Merge branch 'main' into compressed-tensors/run_compressed
c44c513a
ArthurZucker
ArthurZucker approved these changes on 2024-12-13
ArthurZucker ArthurZucker merged e4e404fd into main 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone