diff --git a/docs/_toctree.yml b/docs/source/_toctree.yml
similarity index 100%
rename from docs/_toctree.yml
rename to docs/source/_toctree.yml
diff --git a/docs/index.mdx b/docs/source/index.mdx
similarity index 75%
rename from docs/index.mdx
rename to docs/source/index.mdx
index 4f5776f..008be12 100644
--- a/docs/index.mdx
+++ b/docs/source/index.mdx
@@ -24,21 +24,3 @@ Supported methods include:
 2. Prefix Tuning: [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://aclanthology.org/2021.acl-long.353/), [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://arxiv.org/pdf/2110.07602.pdf)
 3. P-Tuning: [GPT Understands, Too](https://arxiv.org/pdf/2103.10385.pdf)
 4. Prompt Tuning: [The Power of Scale for Parameter-Efficient Prompt Tuning](https://arxiv.org/pdf/2104.08691.pdf) 
-
-## Getting started
-
-```python
-from transformers import AutoModelForSeq2SeqLM
-from peft import get_peft_config, get_peft_model, LoraConfig, TaskType
-
-model_name_or_path = "bigscience/mt0-large"
-tokenizer_name_or_path = "bigscience/mt0-large"
-
-peft_config = LoraConfig(task_type=TaskType.SEQ_2_SEQ_LM, inference_mode=False, r=8, lora_alpha=32, lora_dropout=0.1)
-
-model = AutoModelForSeq2SeqLM.from_pretrained(model_name_or_path)
-model = get_peft_model(model, peft_config)
-model.print_trainable_parameters()
-# output: trainable params: 2359296 || all params: 1231940608 || trainable%: 0.19151053100118282
-```
-
diff --git a/docs/install.mdx b/docs/source/install.mdx
similarity index 100%
rename from docs/install.mdx
rename to docs/source/install.mdx
diff --git a/docs/package_reference/config b/docs/source/package_reference/config
similarity index 100%
rename from docs/package_reference/config
rename to docs/source/package_reference/config
diff --git a/docs/package_reference/peft_model b/docs/source/package_reference/peft_model
similarity index 100%
rename from docs/package_reference/peft_model
rename to docs/source/package_reference/peft_model
diff --git a/docs/package_reference/tuners b/docs/source/package_reference/tuners
similarity index 100%
rename from docs/package_reference/tuners
rename to docs/source/package_reference/tuners
diff --git a/docs/quicktour.mdx b/docs/source/quicktour.mdx
similarity index 98%
rename from docs/quicktour.mdx
rename to docs/source/quicktour.mdx
index e0eb37f..a625aa8 100644
--- a/docs/quicktour.mdx
+++ b/docs/source/quicktour.mdx
@@ -29,9 +29,6 @@ from peft import LoraConfig, TaskType
 peft_config = LoraConfig(task_type=TaskType.SEQ_2_SEQ_LM, inference_mode=False, r=8, lora_alpha=32, lora_dropout=0.1)
 ```
 
-Here, `task_type` is the type of task you are training your model for. 
-For available task types, please refer [TaskType](package_reference/config#peft.config.TaskType).
-
 2. Load the base model you want to fine-tune.
 
 ```python