@@ -149,7 +149,6 @@ Here, we'll show some of the parameters that control the decoding strategies and
...
@@ -149,7 +149,6 @@ Here, we'll show some of the parameters that control the decoding strategies and
### Greedy Search
### Greedy Search
[`generate`] uses greedy search decoding by default so you don't have to pass any parameters to enable it. This means the parameters `num_beams` is set to 1 and `do_sample=False`.
[`generate`] uses greedy search decoding by default so you don't have to pass any parameters to enable it. This means the parameters `num_beams` is set to 1 and `do_sample=False`.
`do_sample=False`. Because it is a default strategy, you do not have to pass any parameters to `generate()` method to enable it.
```python
```python
>>> from transformers import AutoModelForCausalLM, AutoTokenizer
>>> from transformers import AutoModelForCausalLM, AutoTokenizer
...
@@ -303,4 +302,4 @@ The groups are selected to ensure they are distinct enough compared to the other
...
@@ -303,4 +302,4 @@ The groups are selected to ensure they are distinct enough compared to the other
This guide illustrates the main parameters that enable various decoding strategies. More advanced parameters exist for the
This guide illustrates the main parameters that enable various decoding strategies. More advanced parameters exist for the
[`generate`] method, which gives you even further control over the [`generate`] method's behavior.
[`generate`] method, which gives you even further control over the [`generate`] method's behavior.
For the complete list of the available parameters, refer to the [API documentation](./main_classes/text_generation.mdx).
For the complete list of the available parameters, refer to the [API documentation](./main_classes/text_generation.mdx).