Update README.md

README.md

@@ -469,7 +469,7 @@ Try it out by running the following snippet.
 > a FP8 triton kernel for fast accelerated matmuls
 > (`w8a8_block_fp8_matmul_triton`) will be used
 > without any degradation in accuracy. However, if you want to
-> run your model in BF16 see (#transformers-bf16)
+> run your model in BF16 see ([here](#transformers-bf16))
 
 Then load our tokenizer along with the model and generate:
 
@@ -516,6 +516,8 @@ decoded_output = tokenizer.decode(output[len(tokenized["input_ids"][0]):])
 print(decoded_output)
 ```
 
+</details>
+
 #### Transformers BF16
 
 Transformers allows you to automatically convert the checkpoint to Bfloat16. To do so, simply load the model as follows:
@@ -531,8 +533,6 @@ model = Mistral3ForConditionalGeneration.from_pretrained(
 )
 ```
 
-</details>
-
 ## License
 
 This model is licensed under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0.txt).