Remove duplicate wording

microsoft · Nov 15, 2023 · a6dc597 · a6dc597
1 parent 80d694e
commit a6dc597
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/src/routes/blogs/accelerating-llama-2/+page.svelte b/src/routes/blogs/accelerating-llama-2/+page.svelte
@@ -127,7 +127,7 @@
 
 		<p class="mb-4">
 			ONNX Runtime supports multi-GPU inference to enable serving large models. Even in FP16 precision,
-			the LLaMA-2 70B model in FP16 precision requires 140GB. Loading the model requires multiple GPUs 
+			the LLaMA-2 70B model requires 140GB. Loading the model requires multiple GPUs 
 			for inference, even with a powerful NVIDIA A100 80GB GPU.
 		</p>