Added 8-bit weight compression for OVModel #415
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The documentation is not available anymore as the PR was closed or merged. |
alexsu52
pushed a commit
to openvinotoolkit/nncf
that referenced
this pull request
Sep 1, 2023
### Changes Extended data free int8 weight compression algorithm for OpenVINO backend Example (WeightsModel):  PR to optimum huggingface/optimum-intel#415 ### Reason for changes Optimize the model footprint and performance of large models where the size of weights is relatively larger than the size of activations ### Related tickets 117412 ### Tests `tests/openvino/native/quantization/test_weights_compression.py` swin transformer support verified Results Task: lambada_openai | Model |Metric|Value | |Stderr| |--------------|------|-----:|---|-----:| |dolly-v2-3b_original| ppl |5.0144|± |0.1510| | |acc |0.6297|± |0.0067| |dolly-v2-3b_compressed|ppl |4.9868|± |0.1498| | |acc |0.6313|± |0.0067| |Llama-2-7b-chat-hf_original|ppl |3.2788|± |0.0866| | |acc |0.7058|± |0.0063| |Llama-2-7b-chat-hf_compressed|ppl |3.2856|± |0.0869| | |acc |0.7054|± |0.0064|
l-bat
added a commit
to l-bat/nncf
that referenced
this pull request
Sep 1, 2023
…kit#2059) ### Changes Extended data free int8 weight compression algorithm for OpenVINO backend Example (WeightsModel):  PR to optimum huggingface/optimum-intel#415 ### Reason for changes Optimize the model footprint and performance of large models where the size of weights is relatively larger than the size of activations ### Related tickets 117412 ### Tests `tests/openvino/native/quantization/test_weights_compression.py` swin transformer support verified Results Task: lambada_openai | Model |Metric|Value | |Stderr| |--------------|------|-----:|---|-----:| |dolly-v2-3b_original| ppl |5.0144|± |0.1510| | |acc |0.6297|± |0.0067| |dolly-v2-3b_compressed|ppl |4.9868|± |0.1498| | |acc |0.6313|± |0.0067| |Llama-2-7b-chat-hf_original|ppl |3.2788|± |0.0866| | |acc |0.7058|± |0.0063| |Llama-2-7b-chat-hf_compressed|ppl |3.2856|± |0.0869| | |acc |0.7054|± |0.0064|
Contributor
|
I am ok with the PR but failed tests look strange |
AlexKoff88
approved these changes
Sep 5, 2023
l-bat
force-pushed
the
lt/ov_compress_weights
branch
from
f919ccc to
2338c7f
Compare
l-bat
force-pushed
the
lt/ov_compress_weights
branch
from
2338c7f to
6cd4a85
Compare
Contributor
Author
|
@echarlaix there are some failed tests not related to my changes |
echarlaix
reviewed
Sep 20, 2023
Comment on lines
+149
to
+150
| (OVModelForSequenceClassification, "hf-internal-testing/tiny-random-bert", 70, 35), | ||
| (OVModelForCausalLM, "hf-internal-testing/tiny-random-gpt2", 45, 22), |
Collaborator
There was a problem hiding this comment.
What is the difference in the quantization applied on the two models (depending on whether this is a pytorch or an openvino model) ?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Introduced data-free weight compression to 8 bits for
OVBaseModelandOVBaseDecoderModelPR to nncf openvinotoolkit/nncf#2059 was merged
Before submitting