order

docs/dataset-formats/conversation.qmd

@@ -1,6 +1,7 @@
 ---
 title: Conversation
 description: Conversation format for supervised fine-tuning.
+order: 1
 ---
 
 ## Formats

docs/dataset-formats/inst_tune.qmd

@@ -1,6 +1,7 @@
 ---
 title: Instruction Tuning
-description: Instruction tuning formats for supervised fine-tuning. 
+description: Instruction tuning formats for supervised fine-tuning.
+order: 2
 ---
 
 ## alpaca

docs/dataset-formats/pretraining.qmd

@@ -1,6 +1,7 @@
 ---
 title: Pre-training
 description: Data format for a pre-training completion task.
+order: 3
 ---
 
 For pretraining, there is no prompt template or roles.  The only required field is `text`:

docs/dataset-formats/template_free.qmd

@@ -1,6 +1,7 @@
 ---
 title: Template-Free
 description: Construct prompts without a template.
+order: 4
 ---
 
 See [these docs](../input_output.qmd).

docs/dataset-formats/tokenized.qmd

@@ -1,6 +1,7 @@
 ---
 title: Custom Pre-Tokenized Dataset
 description: How to use a custom pre-tokenized dataset.
+order: 5
 ---
 
 - Do not pass a `type:` in your axolotl config.