huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix inline latex

Browse Source
This commit is contained in:
Merve Noyan 2023-09-07 16:46:05 +02:00 committed by GitHub
parent 5f4dcd5a4b
commit 12d9a67752
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/conceptual/quantization.md
View File

@ -6,7 +6,7 @@ TGI offers GPTQ and bits-and-bytes quantization to quantize large language model
GPTQ is a post-training quantization method to make the model smaller. It quantizes each weight by finding a compressed version of that weight, that will yield a minimum mean squared error like below 👇
Given a layer \(l\) with weight matrix \(W_{l}\) and layer input \(X_{l}\), find quantized weight \(\hat{W}_{l}\):
Given a layer \\(l\\) with weight matrix \\(W_{l}\\) and layer input \\(X_{l}\\), find quantized weight \\(\\hat{W}_{l}\\):
$$({\hat{W}_{l}}^{*} = argmin_{\hat{W_{l}}} ||W_{l}X-\hat{W}_{l}X||^{2}_{2})$$