Fix quantization docs typo (#22666)

14fc1a24 · Kirill · GitHub · 3876fc68 · 14fc1a24
Unverified Commit 14fc1a24 authored Apr 10, 2023 by Kirill Committed by GitHub Apr 10, 2023
Hide whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

docs/source/en/main_classes/quantization.mdx docs/source/en/main_classes/quantization.mdx +1 -1

No files found.
--- a/docs/source/en/main_classes/quantization.mdx
+++ b/docs/source/en/main_classes/quantization.mdx
@@ -33,7 +33,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 model_id = "bigscience/bloom-1b7"

 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map == "auto", load_in_8bit=True)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_8bit=True)
 ```

 Then, use your model as you would usually use a [`PreTrainedModel`].