From 3a886bd58cecf3ce78c1eafed1f7d3d16800bccc Mon Sep 17 00:00:00 2001 From: Reid <61492567+reidliu41@users.noreply.github.com> Date: Sun, 25 May 2025 21:05:38 +0800 Subject: [PATCH] [Misc] small improve (#18680) Signed-off-by: reidliu41 Co-authored-by: reidliu41 --- docs/features/quantization/bnb.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/features/quantization/bnb.md b/docs/features/quantization/bnb.md index 710becd7f9..a8dc2476f3 100644 --- a/docs/features/quantization/bnb.md +++ b/docs/features/quantization/bnb.md @@ -15,7 +15,7 @@ pip install bitsandbytes>=0.45.3 vLLM reads the model's config file and supports both in-flight quantization and pre-quantized checkpoint. -You can find bitsandbytes quantized models on . +You can find bitsandbytes quantized models on [Hugging Face](https://huggingface.co/models?search=bitsandbytes). And usually, these repositories have a config.json file that includes a quantization_config section. ## Read quantized checkpoint