sparseml
sparseml copied to clipboard
neuralmagic
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
Implementation of the RigLPruningModifier - a sparse training procedure proposed in the paper https://arxiv.org/abs/1911.11134. **Description** This sparse training procedure performs sparse training of the model with periodic pruning if a...
Small bug related to regression text_classification training. The `label_list` is not instantiated if `is_regression` is true. After this change, you can run the following regression task: ``` !sparseml.transformers.train.text_classification \ --model_name_or_path...
This PR adds SparseML support for causal language modelling tasks from HuggingFace transformers library. This is used to prune generative language models, e.g. GPT-style models. Apart from the standard SparseML...
This PR implements multiple-choice pipeline in HF's transformers library with SparseML integration. It enables commonsense-reasoning experiments proposed in the "Sparsity May Cry benchmark". **Supported datasets/tasks** 1. SWAG: https://arxiv.org/abs/1808.05326 2. Commonsense_QA:...
Issues like https://github.com/neuralmagic/sparseml/issues/1282 are very hard to detect when `global_sparsity: True`, as the final model will have the desired target sparsity but the sparsity scheduler might have followed the wrong...
# Feature Description The `sparseml.transformers.sparsification.modification` package is a set of modifications that are applied to some of the transformer models, to make them compatible with our quantization flows. This PR...
GHA will be green after: https://github.com/neuralmagic/compressed-tensors/pulls lands
Metadata
Owner
Metadata
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models