From 9d764b8a27cefd44ed356aad346383b625b5a097 Mon Sep 17 00:00:00 2001 From: Kyle Sayers Date: Fri, 15 Nov 2024 20:21:46 -0500 Subject: [PATCH] update readme path --- src/llmcompressor/modifiers/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/llmcompressor/modifiers/README.md b/src/llmcompressor/modifiers/README.md index 009b31f5..72ff0b05 100644 --- a/src/llmcompressor/modifiers/README.md +++ b/src/llmcompressor/modifiers/README.md @@ -8,7 +8,7 @@ are relevant only during training. Below is a summary of the key modifiers avail Modifiers that introduce sparsity into a model -### [SparseGPT](./pruning/gptq/base.py) +### [SparseGPT](./pruning/sparsegpt/base.py) One-shot algorithm that uses calibration data to introduce unstructured or structured sparsity into weights. Implementation based on [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://arxiv.org/abs/2301.00774). A small amount of calibration data is used to calculate a Hessian for each layers input activations, this Hessian is then used to