[doc] Fold long code blocks to improve readability (#19926)

Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>

docs/features/quantization/int4.md

@@ -53,51 +53,55 @@ When quantizing weights to INT4, you need sample data to estimate the weight upd
 It's best to use calibration data that closely matches your deployment data.
 For a general-purpose instruction-tuned model, you can use a dataset like `ultrachat`:
 
-```python
-from datasets import load_dataset
+??? Code
 
-NUM_CALIBRATION_SAMPLES = 512
-MAX_SEQUENCE_LENGTH = 2048
+    ```python
+    from datasets import load_dataset
 
-# Load and preprocess the dataset
-ds = load_dataset("HuggingFaceH4/ultrachat_200k", split="train_sft")
-ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES))
+    NUM_CALIBRATION_SAMPLES = 512
+    MAX_SEQUENCE_LENGTH = 2048
 
-def preprocess(example):
-    return {"text": tokenizer.apply_chat_template(example["messages"], tokenize=False)}
-ds = ds.map(preprocess)
+    # Load and preprocess the dataset
+    ds = load_dataset("HuggingFaceH4/ultrachat_200k", split="train_sft")
+    ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES))
 
-def tokenize(sample):
-    return tokenizer(sample["text"], padding=False, max_length=MAX_SEQUENCE_LENGTH, truncation=True, add_special_tokens=False)
-ds = ds.map(tokenize, remove_columns=ds.column_names)
-```
+    def preprocess(example):
+        return {"text": tokenizer.apply_chat_template(example["messages"], tokenize=False)}
+    ds = ds.map(preprocess)
+
+    def tokenize(sample):
+        return tokenizer(sample["text"], padding=False, max_length=MAX_SEQUENCE_LENGTH, truncation=True, add_special_tokens=False)
+    ds = ds.map(tokenize, remove_columns=ds.column_names)
+    ```
 
 ### 3. Applying Quantization
 
 Now, apply the quantization algorithms:
 
-```python
-from llmcompressor.transformers import oneshot
-from llmcompressor.modifiers.quantization import GPTQModifier
-from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
+??? Code
 
-# Configure the quantization algorithms
-recipe = GPTQModifier(targets="Linear", scheme="W4A16", ignore=["lm_head"])
+    ```python
+    from llmcompressor.transformers import oneshot
+    from llmcompressor.modifiers.quantization import GPTQModifier
+    from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
 
-# Apply quantization
-oneshot(
-    model=model,
-    dataset=ds,
-    recipe=recipe,
-    max_seq_length=MAX_SEQUENCE_LENGTH,
-    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
-)
+    # Configure the quantization algorithms
+    recipe = GPTQModifier(targets="Linear", scheme="W4A16", ignore=["lm_head"])
 
-# Save the compressed model: Meta-Llama-3-8B-Instruct-W4A16-G128
-SAVE_DIR = MODEL_ID.split("/")[1] + "-W4A16-G128"
-model.save_pretrained(SAVE_DIR, save_compressed=True)
-tokenizer.save_pretrained(SAVE_DIR)
-```
+    # Apply quantization
+    oneshot(
+        model=model,
+        dataset=ds,
+        recipe=recipe,
+        max_seq_length=MAX_SEQUENCE_LENGTH,
+        num_calibration_samples=NUM_CALIBRATION_SAMPLES,
+    )
+
+    # Save the compressed model: Meta-Llama-3-8B-Instruct-W4A16-G128
+    SAVE_DIR = MODEL_ID.split("/")[1] + "-W4A16-G128"
+    model.save_pretrained(SAVE_DIR, save_compressed=True)
+    tokenizer.save_pretrained(SAVE_DIR)
+    ```
 
 This process creates a W4A16 model with weights quantized to 4-bit integers.
 
@@ -137,34 +141,36 @@ $ lm_eval --model vllm \
 
 The following is an example of an expanded quantization recipe you can tune to your own use case:
 
-```python
-from compressed_tensors.quantization import (
-    QuantizationArgs,
-    QuantizationScheme,
-    QuantizationStrategy,
-    QuantizationType,
-) 
-recipe = GPTQModifier(
-    targets="Linear",
-    config_groups={
-        "config_group": QuantizationScheme(
-            targets=["Linear"],
-            weights=QuantizationArgs(
-                num_bits=4,
-                type=QuantizationType.INT,
-                strategy=QuantizationStrategy.GROUP,
-                group_size=128,
-                symmetric=True,
-                dynamic=False,
-                actorder="weight",
+??? Code
+
+    ```python
+    from compressed_tensors.quantization import (
+        QuantizationArgs,
+        QuantizationScheme,
+        QuantizationStrategy,
+        QuantizationType,
+    ) 
+    recipe = GPTQModifier(
+        targets="Linear",
+        config_groups={
+            "config_group": QuantizationScheme(
+                targets=["Linear"],
+                weights=QuantizationArgs(
+                    num_bits=4,
+                    type=QuantizationType.INT,
+                    strategy=QuantizationStrategy.GROUP,
+                    group_size=128,
+                    symmetric=True,
+                    dynamic=False,
+                    actorder="weight",
+                ),
             ),
-        ),
-    },
-    ignore=["lm_head"],
-    update_size=NUM_CALIBRATION_SAMPLES,
-    dampening_frac=0.01
-)
-```
+        },
+        ignore=["lm_head"],
+        update_size=NUM_CALIBRATION_SAMPLES,
+        dampening_frac=0.01
+    )
+    ```
 
 ## Troubleshooting and Support