From f32584fd5e1fb0ed91606335db53be6b13462583 Mon Sep 17 00:00:00 2001
From: Jack-Khuu <jack.khuu.7@gmail.com>
Date: Fri, 22 Nov 2024 01:22:43 -0500
Subject: [PATCH] Update quantization.md link to quantize.py

https://github.com/pytorch/torchchat/issues/1385
---
 docs/quantization.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/quantization.md b/docs/quantization.md
index 3415d8cb8..5007946bb 100644
--- a/docs/quantization.md
+++ b/docs/quantization.md
@@ -59,7 +59,7 @@ for valid `bitwidth` and `groupsize` values.
 | linear with dynamic activations (symmetric) | `'{"linear:a8w4dq" : {"groupsize" : <groupsize>}}'`|
 | embedding | `'{"embedding": {"bitwidth": <bitwidth>, "groupsize":<groupsize>}}'` |
 
-See the available quantization schemes [here](https://github.com/pytorch/torchchat/blob/main/torchchat/utils/quantize.py#L1260-L1266).
+See the available quantization schemes [here](https://github.com/pytorch/torchchat/blob/b809b69e03f8f4b75a4b27b0778f0d3695ce94c2/torchchat/utils/quantize.py#L887-L894).
 
 In addition to quantization, the [accelerator](model_customization.md#device)
 and [precision](model_customization.md#model-precision) can also be specified.