diff --git a/course/en/chapter11/section3.ipynb b/course/en/chapter11/section3.ipynb
index 7dd5cdd8b..cf2519302 100644
--- a/course/en/chapter11/section3.ipynb
+++ b/course/en/chapter11/section3.ipynb
@@ -25,7 +25,7 @@
    "outputs": [],
    "source": [
     "# Install the requirements in Google Colab\n",
-    "# !pip install transformers datasets trl huggingface_hub\n",
+    "# !pip install transformers==4.57.3 datasets==4.4.2 trl==0.26.2 huggingface_hub\n",
     "\n",
     "# Authenticate to Hugging Face\n",
     "\n",
@@ -44,7 +44,7 @@
     "# Import necessary libraries\n",
     "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
     "from datasets import load_dataset\n",
-    "from trl import SFTConfig, SFTTrainer, setup_chat_format\n",
+    "from trl import SFTConfig, SFTTrainer\n",
     "import torch\n",
     "\n",
     "device = (\n",
@@ -60,8 +60,12 @@
     ").to(device)\n",
     "tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path=model_name)\n",
     "\n",
-    "# Set up the chat format\n",
-    "model, tokenizer = setup_chat_format(model=model, tokenizer=tokenizer)\n",
+    "# Tokenizer Chat Template\n",
+    "tokenizer.chat_template = (\n",
+    "    \"{% for message in messages %}\"\n",
+    "    \"{{'<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n'}}\"\n",
+    "    \"{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}\"\n",
+    ")\n",
     "\n",
     "# Set our name for the finetune to be saved &/ uploaded to\n",
     "finetune_name = \"SmolLM2-FT-MyDataset\"\n",
@@ -153,7 +157,7 @@
     "    learning_rate=5e-5,  # Common starting point for fine-tuning\n",
     "    logging_steps=10,  # Frequency of logging training metrics\n",
     "    save_steps=100,  # Frequency of saving model checkpoints\n",
-    "    evaluation_strategy=\"steps\",  # Evaluate the model at regular intervals\n",
+    "    eval_strategy=\"steps\",  # Evaluate the model at regular intervals\n",
     "    eval_steps=50,  # Frequency of evaluation\n",
     "    use_mps_device=(\n",
     "        True if device == \"mps\" else False\n",
@@ -161,12 +165,12 @@
     "    hub_model_id=finetune_name,  # Set a unique name for your model\n",
     ")\n",
     "\n",
-    "# Initialize the SFTTrainer\n",
+    "    # Initialize the SFTTrainer\n",
     "trainer = SFTTrainer(\n",
     "    model=model,\n",
     "    args=sft_config,\n",
     "    train_dataset=ds[\"train\"],\n",
-    "    tokenizer=tokenizer,\n",
+    "    processing_class=tokenizer,\n",
     "    eval_dataset=ds[\"test\"],\n",
     ")\n",
     "\n",
diff --git a/course/en/chapter11/section4.ipynb b/course/en/chapter11/section4.ipynb
index 9028d4771..94aedea90 100644
--- a/course/en/chapter11/section4.ipynb
+++ b/course/en/chapter11/section4.ipynb
@@ -41,7 +41,7 @@
    "outputs": [],
    "source": [
     "# Install the requirements in Google Colab\n",
-    "# !pip install transformers datasets trl huggingface_hub\n",
+    "# !pip install transformers==4.57.3 datasets==4.4.2 trl==0.26.2 peft==0.18.0 huggingface_hub\n",
     "\n",
     "# Authenticate to Hugging Face\n",
     "\n",
@@ -135,7 +135,7 @@
     "# Import necessary libraries\n",
     "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
     "from datasets import load_dataset\n",
-    "from trl import SFTConfig, SFTTrainer, setup_chat_format\n",
+    "from trl import SFTConfig, SFTTrainer\n",
     "import torch\n",
     "\n",
     "device = (\n",
@@ -152,8 +152,12 @@
     ").to(device)\n",
     "tokenizer = AutoTokenizer.from_pretrained(pretrained_model_name_or_path=model_name)\n",
     "\n",
-    "# Set up the chat format\n",
-    "model, tokenizer = setup_chat_format(model=model, tokenizer=tokenizer)\n",
+    "# Tokenizer Chat Template\n",
+    "tokenizer.chat_template = (\n",
+    "    \"{% for message in messages %}\"\n",
+    "    \"{{'<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n'}}\"\n",
+    "    \"{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}\"\n",
+    ")\n",
     "\n",
     "# Set our name for the finetune to be saved &/ uploaded to\n",
     "finetune_name = \"SmolLM2-FT-MyDataset\"\n",
@@ -223,6 +227,8 @@
    },
    "outputs": [],
    "source": [
+    "max_seq_length = 1512  # max sequence length for model and packing of the dataset\n",
+    "\n",
     "# Training configuration\n",
     "# Hyperparameters based on QLoRA paper recommendations\n",
     "args = SFTConfig(\n",
@@ -250,6 +256,12 @@
     "    # Integration settings\n",
     "    push_to_hub=False,  # Don't push to HuggingFace Hub\n",
     "    report_to=\"none\",  # Disable external logging\n",
+    "    max_length=max_seq_length,  # Maximum sequence length\n",
+    "    packing=True,  # Enable input packing for efficiency\n",
+    "    dataset_kwargs={\n",
+    "        \"add_special_tokens\": False,  # Special tokens handled by template\n",
+    "        \"append_concat_token\": False,  # No additional separator needed\n",
+    "    },\n",
     ")"
    ]
   },
@@ -270,21 +282,13 @@
    },
    "outputs": [],
    "source": [
-    "max_seq_length = 1512  # max sequence length for model and packing of the dataset\n",
-    "\n",
     "# Create SFTTrainer with LoRA configuration\n",
     "trainer = SFTTrainer(\n",
     "    model=model,\n",
     "    args=args,\n",
     "    train_dataset=dataset[\"train\"],\n",
     "    peft_config=peft_config,  # LoRA configuration\n",
-    "    max_seq_length=max_seq_length,  # Maximum sequence length\n",
-    "    tokenizer=tokenizer,\n",
-    "    packing=True,  # Enable input packing for efficiency\n",
-    "    dataset_kwargs={\n",
-    "        \"add_special_tokens\": False,  # Special tokens handled by template\n",
-    "        \"append_concat_token\": False,  # No additional separator needed\n",
-    "    },\n",
+    "    processing_class=tokenizer\n",
     ")"
    ]
   },