updates

_quarto.yml

@@ -19,35 +19,47 @@ website:
       href: https://discord.gg/7m9sfhzaf3
 
   sidebar:
-      pinned: true
-      collapse-level: 2
-      style: docked
-      contents:
-        - text: Home
-          href: index.qmd
-        - section: "How-To Guides"
-          contents:
-          # TODO Edit folder structure after we have more docs.
-            - docs/debugging.qmd
-            - docs/multipack.qmd
-            - docs/fsdp_qlora.qmd
-            - docs/input_output.qmd
-            - docs/rlhf.qmd
-            - docs/nccl.qmd
-            - docs/mac.qmd
-            - docs/multi-node.qmd
-            - docs/unsloth.qmd
-            - docs/amd_hpc.qmd
-        - section: "Dataset Formats"
-          contents: docs/dataset-formats/*
-        - section: "Reference"
-          contents:
-            - docs/config.qmd
-        - docs/faq.qmd
-
+    pinned: true
+    collapse-level: 2
+    style: docked
+    contents:
+      - text: Home
+        href: index.qmd
+      - section: "How-To Guides"
+        contents:
+          - docs/debugging.qmd
+          - docs/multipack.qmd
+          - docs/fsdp_qlora.qmd
+          - docs/input_output.qmd
+          - docs/rlhf.qmd
+          - docs/nccl.qmd
+          - docs/mac.qmd
+          - docs/multi-node.qmd
+          - docs/unsloth.qmd
+          - docs/amd_hpc.qmd
+      - section: "Dataset Formats"
+        contents: docs/dataset-formats/*
+      - section: "Reference"
+        contents:
+          - docs/config.qmd
+      - section: "API Reference"
+        contents: "{{ api_contents }}"
+      - text: "FAQ"
+        href: docs/faq.qmd
 
 format:
   html:
     theme: materia
     css: styles.css
     toc: true
+
+quartodoc:
+  package: axolotl
+  parser: google
+  dir: api
+  sections:
+    - title: Core API
+      desc: Core functionality of Axolotl
+
+metadata-files:
+  - api/_sidebar.yml

_sidebar.yml

@@ -0,0 +1,17 @@
+website:
+  sidebar:
+  - collapse-level: 2
+    contents:
+    - href: introduction.qmd
+      text: Introduction
+    - contents:
+      - reference/index.qmd
+      - contents: []
+        section: axolotl
+      section: Reference
+    - href: basics-summary.qmd
+      text: Basics
+    id: reference
+    search: true
+    style: docked
+  - id: dummy-sidebar

api/ConstantLengthDataset.qmd

@@ -0,0 +1,11 @@
+# ConstantLengthDataset { #axolotl.ConstantLengthDataset }
+
+```python
+ConstantLengthDataset(self, tokenizer, datasets, seq_length=2048)
+```
+
+Iterable dataset that returns constant length chunks of tokens from stream of text files.
+    Args:
+        tokenizer (Tokenizer): The processor used for processing the data.
+        dataset (dataset.Dataset): Dataset with text files.
+        seq_length (int): Length of token sequences to return.

api/TokenizedPromptDataset.qmd

@@ -0,0 +1,19 @@
+# TokenizedPromptDataset { #axolotl.TokenizedPromptDataset }
+
+```python
+TokenizedPromptDataset(
+    self,
+    prompt_tokenizer,
+    dataset,
+    process_count=None,
+    keep_in_memory=False,
+    **kwargs,
+)
+```
+
+Dataset that returns tokenized prompts from a stream of text files.
+    Args:
+        prompt_tokenizer (PromptTokenizingStrategy): The prompt tokenizing method for processing the data.
+        dataset (dataset.Dataset): Dataset with text files.
+        process_count (int): Number of processes to use for tokenizing.
+        keep_in_memory (bool): Whether to keep the tokenized dataset in memory.

api/choose_config.qmd

@@ -0,0 +1,28 @@
+# choose_config { #axolotl.choose_config }
+
+```python
+choose_config(path)
+```
+
+Helper method for choosing a `axolotl` config YAML file (considering only files
+ending with `.yml` or `.yaml`). If more than one config file exists in the passed
+`path`, the user is prompted to choose one.
+
+## Parameters {.doc-section .doc-section-parameters}
+
+| Name   | Type   | Description                                   | Default    |
+|--------|--------|-----------------------------------------------|------------|
+| path   | Path   | Directory in which config file(s) are stored. | _required_ |
+
+## Returns {.doc-section .doc-section-returns}
+
+| Name   | Type   | Description                                                                      |
+|--------|--------|----------------------------------------------------------------------------------|
+|        | str    | Path to either (1) the sole YAML file, or (2) if more than one YAML files exist, |
+|        | str    | the user-selected YAML file.                                                     |
+
+## Raises {.doc-section .doc-section-raises}
+
+| Name   | Type       | Description                                     |
+|--------|------------|-------------------------------------------------|
+|        | ValueError | If no YAML files are found in the given `path`. |

api/index.qmd

@@ -0,0 +1,5 @@
+# Function reference {.doc .doc-index}
+
+## Core API
+
+Core functionality of Axolotl

api/load_cfg.qmd

@@ -0,0 +1,21 @@
+# load_cfg { #axolotl.load_cfg }
+
+```python
+load_cfg(config=Path('examples/'), **kwargs)
+```
+
+Loads the `axolotl` configuration stored at `config`, validates it, and performs
+various setup.
+
+## Parameters {.doc-section .doc-section-parameters}
+
+| Name   | Type               | Description                                                  | Default             |
+|--------|--------------------|--------------------------------------------------------------|---------------------|
+| config | Union\[str, Path\] | Path (local or remote) to `axolotl` config YAML file.        | `Path('examples/')` |
+| kwargs |                    | Additional keyword arguments to override config file values. | `{}`                |
+
+## Returns {.doc-section .doc-section-returns}
+
+| Name   | Type        | Description                                         |
+|--------|-------------|-----------------------------------------------------|
+|        | DictDefault | `DictDefault` mapping configuration keys to values. |

api/validate_config.qmd

@@ -0,0 +1,5 @@
+# validate_config { #axolotl.validate_config }
+
+```python
+validate_config(cfg, capabilities=None, env_capabilities=None)
+```

objects.json

@@ -0,0 +1 @@
+{"project": "axolotl", "version": "0.0.9999", "count": 0, "items": []}

reference/index.qmd

@@ -0,0 +1,3 @@
+# API Reference {.doc .doc-index}
+
+## Core API

requirements-dev.txt

@@ -2,3 +2,5 @@ pre-commit
 black
 mypy
 types-requests
+quartodoc
+quarto-cli

src/axolotl/__init__.py

@@ -2,6 +2,20 @@
 
 import pkgutil
 
-__path__ = pkgutil.extend_path(__path__, __name__)  # Make this a namespace package
+from .cli.config import choose_config, load_cfg, validate_config
+from .datasets import ConstantLengthDataset, TokenizedPromptDataset
+from .evaluate import evaluate
+from .train import train
 
+__path__ = pkgutil.extend_path(__path__, __name__)  # Make this a namespace package
 __version__ = "0.6.0"
+
+__all__ = [
+    "train",
+    "evaluate",
+    "TokenizedPromptDataset",
+    "ConstantLengthDataset",
+    "load_cfg",
+    "choose_config",
+    "validate_config",
+]