Generate: inner decoding methods are no longer public (#29437)

docs/source/en/generation_strategies.md

@@ -389,3 +389,6 @@ just like in multinomial sampling. However, in assisted decoding, reducing the t
 >>> tokenizer.batch_decode(outputs, skip_special_tokens=True)
 ['Alice and Bob are going to the same party. It is a small party, in a small']
 ```
+
+Alternativelly, you can also set the `prompt_lookup_num_tokens` to trigger n-gram based assisted decoding, as opposed
+to model based assisted decoding. You can read more about it [here](https://twitter.com/joao_gante/status/1747322413006643259).

docs/source/en/internal/generation_utils.md

@@ -16,16 +16,7 @@ rendered properly in your Markdown viewer.
 
 # Utilities for Generation
 
-This page lists all the utility functions used by [`~generation.GenerationMixin.generate`],
-[`~generation.GenerationMixin.greedy_search`],
-[`~generation.GenerationMixin.contrastive_search`],
-[`~generation.GenerationMixin.sample`],
-[`~generation.GenerationMixin.beam_search`],
-[`~generation.GenerationMixin.beam_sample`],
-[`~generation.GenerationMixin.group_beam_search`], and
-[`~generation.GenerationMixin.constrained_beam_search`].
-
-Most of those are only useful if you are studying the code of the generate methods in the library.
+This page lists all the utility functions used by [`~generation.GenerationMixin.generate`].
 
 ## Generate Outputs
 
@@ -376,4 +367,4 @@ A [`Constraint`] can be used to force the generation to include specific tokens
 
 [[autodoc]] StaticCache
     - update
-    - get_seq_length
+    - get_seq_length

docs/source/en/main_classes/text_generation.md

@@ -43,13 +43,6 @@ like token streaming.
 [[autodoc]] generation.GenerationMixin
 	- generate
 	- compute_transition_scores
-	- greedy_search
-	- sample
-	- beam_search
-	- beam_sample
-	- contrastive_search
-	- group_beam_search
-	- constrained_beam_search
 
 ## TFGenerationMixin
 

docs/source/ja/internal/generation_utils.md

@@ -17,15 +17,6 @@ rendered properly in your Markdown viewer.
 # 発電用ユーティリティ
 
 このページには、[`~generation.GenerationMixin.generate`] で使用されるすべてのユーティリティ関数がリストされています。
-[`~generation.GenerationMixin.greedy_search`],
-[`~generation.GenerationMixin.contrastive_search`],
-[`~generation.GenerationMixin.sample`],
-[`~generation.GenerationMixin.beam_search`],
-[`~generation.GenerationMixin.beam_sample`],
-[`~generation.GenerationMixin.group_beam_search`]、および
-[`~generation.GenerationMixin.constrained_beam_search`]。
-
-これらのほとんどは、ライブラリ内の生成メソッドのコードを学習する場合にのみ役に立ちます。
 
 ## 出力を生成する
 

docs/source/ja/main_classes/text_generation.md

@@ -43,13 +43,6 @@ rendered properly in your Markdown viewer.
 [[autodoc]] generation.GenerationMixin
 	- generate
 	- compute_transition_scores
-	- greedy_search
-	- sample
-	- beam_search
-	- beam_sample
-	- contrastive_search
-	- group_beam_search
-	- constrained_beam_search
 
 ## TFGenerationMixin
 

docs/source/zh/internal/generation_utils.md

@@ -16,16 +16,7 @@ rendered properly in your Markdown viewer.
 
 # 用于生成的工具
 
-此页面列出了所有由 [`~generation.GenerationMixin.generate`],
-[`~generation.GenerationMixin.greedy_search`],
-[`~generation.GenerationMixin.contrastive_search`],
-[`~generation.GenerationMixin.sample`],
-[`~generation.GenerationMixin.beam_search`],
-[`~generation.GenerationMixin.beam_sample`],
-[`~generation.GenerationMixin.group_beam_search`], 和
-[`~generation.GenerationMixin.constrained_beam_search`]使用的实用函数。
-
-其中大多数仅在您研究库中生成方法的代码时才有用。
+此页面列出了所有由 [`~generation.GenerationMixin.generate`]。
 
 ## 生成输出
 

docs/source/zh/main_classes/text_generation.md

@@ -38,13 +38,6 @@ rendered properly in your Markdown viewer.
 [[autodoc]] generation.GenerationMixin
 	- generate
 	- compute_transition_scores
-	- greedy_search
-	- sample
-	- beam_search
-	- beam_sample
-	- contrastive_search
-	- group_beam_search
-	- constrained_beam_search
 
 ## TFGenerationMixin