Squashed commit of the following:

commit 7a9592b
Author: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
Date:   Tue Nov 4 14:32:04 2025 -0700

    🐍 Drop Python 3.9 (huggingface#4183)

commit 7f15a7f
Author: Harras Mansoor <98635627+Harras3@users.noreply.github.com>
Date:   Wed Nov 5 02:06:31 2025 +0500

    Removed outdated warning about batch contamination (huggingface#4423)

commit 8b0a3ce
Author: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
Date:   Tue Nov 4 21:37:39 2025 +0100

    Update tokenizer apply_chat_template with return_dict=True default (huggingface#4448)

commit d9f9e2b
Author: Pramodith Ballapuram <16939722+pramodith@users.noreply.github.com>
Date:   Tue Nov 4 19:56:58 2025 +0000

    Support casting to fp32 when word embeddings are tied to lm_head (huggingface#4446)

commit 4e138ab
Author: Sergio Paniego Blanco <sergiopaniegoblanco@gmail.com>
Date:   Tue Nov 4 15:15:23 2025 +0100

    Upload notebook with T4 selected (huggingface#4449)

Author: qgallouedec

.github/workflows/tests.yml

@@ -40,7 +40,7 @@ jobs:
     name: Tests
     strategy:
       matrix:
-        python-version: ['3.9', '3.10', '3.11', '3.12', '3.13']
+        python-version: ['3.10', '3.11', '3.12', '3.13']
       fail-fast: false
     runs-on:
       group: aws-g4dn-2xlarge

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.10
+    rev: v0.13.3
     hooks:
       - id: ruff-check
         types_or: [ python, pyi ]

CONTRIBUTING.md

@@ -285,24 +285,6 @@ def replicate_str(string: str, n: int, sep: str = " ") -> str:
 * **Definite Articles:** Removed definite articles where possible to streamline language. (Eg: Changed "The string to replicate" to "String to replicate")
 * **Type Annotations:**
   * Always include type definitions, indicating if a parameter is optional and specifying the default value.
-  * Note that `Optional` means that the value can be `None`, and `*optional*` means that it is not required for the user to pass a value.
-    E.g., for arguments that can't be `None` and aren't required:
-
-    ```txt
-    foo (`int`, *optional*, defaults to `4`):
-    ```
-
-    For arguments that can be `None` and are required:
-
-    ```txt
-    foo (`Optional[int]`):
-    ```
-
-    for arguments that can be `None` and aren't required (in this case, if the default value is `None`, you can omit it):
-
-    ```txt
-    foo (`Optional[int]`, *optional*):
-    ```
 
 * **String Defaults:**
   * Ensured that default string values are wrapped in double quotes:

docs/source/lora_without_regret.md

@@ -141,7 +141,7 @@ For reinforcement learning, the blog uses a math reasoning task that we can repr
 ```python
 def strip_reasoning_accuracy_reward(
     completions: list[list[dict[str, str]]], solution: list[str], **kwargs
-) -> list[Optional[float]]:
+) -> list[float | None]:
     """Reward function that strips reasoning tags and checks mathematical accuracy.
 
     This function:

docs/source/reducing_memory_usage.md

@@ -90,9 +90,6 @@ from trl import SFTConfig
 training_args = SFTConfig(..., packing=True, max_length=512)
 ```
 
-> [!WARNING]
-> Packing may cause batch contamination, where adjacent sequences influence one another. This can be problematic for some applications. For more details, see [#1230](https://github.com/huggingface/trl/issues/1230).
-
 ## Liger for reducing peak memory usage
 
 > [Liger Kernel](https://github.com/linkedin/Liger-Kernel) is a collection of Triton kernels designed specifically for LLM training. It can effectively increase multi-GPU training throughput by 20% and reduce memory usage by 60%.

examples/datasets/hh-rlhf-helpful-base.py

@@ -14,7 +14,6 @@
 
 import re
 from dataclasses import dataclass, field
-from typing import Optional
 
 from datasets import load_dataset
 from huggingface_hub import ModelCard
@@ -42,15 +41,15 @@ class ScriptArguments:
     repo_id: str = field(
         default="trl-lib/hh-rlhf-helpful-base", metadata={"help": "Hugging Face repository ID to push the dataset to."}
     )
-    dataset_num_proc: Optional[int] = field(
+    dataset_num_proc: int | None = field(
         default=None, metadata={"help": "Number of workers to use for dataset processing."}
     )
 
 
 def common_start(str1: str, str2: str) -> str:
     # Zip the two strings and iterate over them together
     common_chars = []
-    for c1, c2 in zip(str1, str2):
+    for c1, c2 in zip(str1, str2, strict=True):
         if c1 == c2:
             common_chars.append(c1)
         else:

examples/datasets/llava_instruct_mix.py

@@ -14,7 +14,6 @@
 
 import ast
 from dataclasses import dataclass, field
-from typing import Optional
 
 from datasets import load_dataset
 from huggingface_hub import ModelCard
@@ -43,7 +42,7 @@ class ScriptArguments:
         default="trl-lib/llava-instruct-mix",
         metadata={"help": "Hugging Face repository ID to push the dataset to."},
     )
-    dataset_num_proc: Optional[int] = field(
+    dataset_num_proc: int | None = field(
         default=None,
         metadata={"help": "Number of workers to use for dataset processing."},
     )

examples/datasets/lm-human-preferences-descriptiveness.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 
 from dataclasses import dataclass, field
-from typing import Optional
 
 from datasets import load_dataset
 from huggingface_hub import ModelCard
@@ -42,7 +41,7 @@ class ScriptArguments:
         default="trl-lib/lm-human-preferences-descriptiveness",
         metadata={"help": "Hugging Face repository ID to push the dataset to."},
     )
-    dataset_num_proc: Optional[int] = field(
+    dataset_num_proc: int | None = field(
         default=None,
         metadata={"help": "Number of workers to use for dataset processing."},
     )

examples/datasets/lm-human-preferences-sentiment.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 
 from dataclasses import dataclass, field
-from typing import Optional
 
 from datasets import load_dataset
 from huggingface_hub import ModelCard
@@ -42,7 +41,7 @@ class ScriptArguments:
         default="trl-lib/lm-human-preferences-sentiment",
         metadata={"help": "Hugging Face repository ID to push the dataset to."},
     )
-    dataset_num_proc: Optional[int] = field(
+    dataset_num_proc: int | None = field(
         default=None,
         metadata={"help": "Number of workers to use for dataset processing."},
     )

examples/datasets/math_shepherd.py

@@ -15,7 +15,6 @@
 import re
 from dataclasses import dataclass, field
 from itertools import chain
-from typing import Optional
 
 from datasets import load_dataset
 from huggingface_hub import ModelCard
@@ -44,7 +43,7 @@ class ScriptArguments:
         default="trl-lib/math_shepherd",
         metadata={"help": "Hugging Face repository ID to push the dataset to."},
     )
-    dataset_num_proc: Optional[int] = field(
+    dataset_num_proc: int | None = field(
         default=None,
         metadata={"help": "Number of workers to use for dataset processing."},
     )
@@ -64,7 +63,7 @@ def process_example(example):
     labels = [example["label"][idx] == "+" for idx in indexes]
 
     # Split the inputs into steps (caution, the first step is missing here, it is the prompt)
-    steps = [inputs[i:j] for i, j in zip(chain([0], indexes), chain(indexes, [None]))]
+    steps = [inputs[i:j] for i, j in zip(chain([0], indexes), chain(indexes, [None]), strict=True)]
 
     # Remove the last step (single ⶻ)
     steps = steps[:-1]