sparseml

sparseml copied to clipboard

model size became bigger after pruning model

14

my code is .. `%run train.py --batch-size 12 --img 640 --multi-scale --cfg ../models/yolov5s.yaml --device 0 --weights "D:\sparseml\integrations\ultralytics-yolov5\yolov5\runs\train\exp21\weights\last.pt" \ --data ./data/custom.yaml --hyp data/hyp.scratch_2.yaml --recipe ../recipes/yolov5s.pruned.md ` It became a larger yolov5s...

kuonumber

This PR creates a base class for knowledge distillation modifiers and changes the existing knowledge distillation modifier to inherit from the base class. The goal of this change is to...

anmarques

currently in runs of composed staged recipes, modifier finalization only occurs at the end of the entire run (after all stages). this may cause issues because when a stage is...

bfineran

Implement mask-transfer between models at init

2

* masks are transferred from the given model at initialization * to keep masks on, one should add ConstantPruningModifier in the yaml recipe * add apply_weight_mask function to transfer masks...

eldarkurtic

onnxruntime-gpu - is there a reson this is not an option?

4

**Is your feature request related to a problem? Please describe.** built the onnxruntime-gpu to fulfill requirement ``` Could not find a version that satisfies the requirement onnxruntime>=1.0.0 (from sparseml[torch,torchvision]) (from...

meeki007

Add support to total batch size argument for transformers transfer learning

2

Created the NMTrainingArguments that inherits from HF's TrainingArguments. This class allows one to add arguments to the training script and handling potential conflicts with other arguments. In particular, added "total_train_batch_size"...

anmarques

speed

6

the size of pruned and not pruned is same ---> 14.4M the spedd of that is same ,too What do I need to do to make it go fasteri in...

aimen123

in collaboration with @anmarques goal of this PR is to add a pass to emulate the INT32 quantization of a FC layer's bias add to accurately match what happens during...

bfineran

MT5 model convertion with sparseml

8

Hello, I am trying to converting mt5 model to onnx runtime. But i can see that model is not supported. Is there any work around. Error: `Unrecognized configuration class for...

OriAlpha

Add args for black/isort/flake in the Makefile

2

**Is your feature request related to a problem? Please describe.** It could be useful to have an option to specify some arguments to black/isort/flake8 when running `make quality` and `make...

eldarkurtic