> ## Documentation Index
> Fetch the complete documentation index at: https://training-docs.cerebras.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Token Generators
> Learn about supported Token Generators for data preprocessing.
Token generators convert raw data into tokenized formats suitable for machine learning models, ensuring efficient and effective data processing. This guide covers the configuration of pre-built and custom token generators, along with examples and use cases.
## Pre-Built Token Generators
Cerebras Model Zoo provides a comprehensive suite of pre-built token generators tailored to support various stages and tasks in the development of LLMs. The initialization of these token generators is dependent on the `mode` parameter that is specified in the config file (refer to [Modes](../../../model-zoo/components/data-preprocessing/data-preprocessing#modes).
### Flags Supported by Pre-Built Token Generators
This section lists parameters that can be used for `PretrainingTokenGenerator`.
| Flag | Default Value | Description |
| ------------------------- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| pack\_sequences | True | Concatenate a document smaller than maximum sequence length with other documents, instead of filling it with Padding token. |
| inverted\_mask | False | If False, 0 represents masked positions. If True 1 represents masked positions. |
| seed | 0 | Random seed used for generating short sequences |
| short\_seq\_prob | 0.0 | Probability of creating sequences which are shorter than the maximum sequence length. |
| split\_text\_to\_tokenize | False | Whether to split the text into smaller chunks before tokenization. This is helpful for very long documents with tokenizers such as Llama tokenizer which performs quadratically in the text length. |
| chunk\_len\_to\_split | 2000 | Length of the text chunks to split the text into before tokenization for slower tokenizers. Could be optionally used with the above flag split\_text\_to\_tokenize. Without the previous flag, this argument will be ignored. |
| remove\_bos\_in\_chunks | False | Whether to remove the BOS token from the beginning of the chunks. Set this to True when using split\_test\_to\_tokenize and chunk\_len\_to\_split to avoid having multiple BOS tokens in the middle of the text. Not applicable to all tokenizers. |
In this case, it also uses all the config paramaters that are used by `PretrainingTokenGenerator`, in addition to the ones specified below.
| Flag | Default Value | Description |
| ----------------- | ------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| mlm\_fraction | 0.15 | Fraction of tokens to be masked in MLM tasks. |
| mlm\_with\_gather | False | MLM processing mode. When set to True the length of the returned labels is equal to mlm\_fraction \* msl, else it is equal to msl |
| ignore\_index | -100 | Required when mlm\_with\_gather is set to False. Presence of ignore\_index value at a position in the labels indicates that this position will not be used for loss calculation. |
| excluded\_tokens | \[‘\’, ‘\’, ‘\’, ‘\’, ‘\’, ‘\’] | Tokens to be excluded when masking. Provided only through YAML config. |
This section lists down parameters that can be used for `VSLFineTuningTokenGenerator`.
`VSLFineTuningTokenGenerator` also uses the config paramaters that are used by `FineTuningTokenGenerator`, in addition to the ones specified below.
| Flag | Default Value | Description |
| -------------------- | ------------- | --------------------------------------------------------- |
| use\_vsl | True | Generate examples with multiple sequences packed together |
| position\_ids\_dtype | int32 | dtype of token position ids. |
Note
Increasing the read chunk size will increase the packing factor of VSL. So, the user needs to figure out the tradeoff between higher packing and processing time depending on the dataset’s packing factor.
This section lists down parameters that can be used for `VSLPretrainingTokenGenerator`. `use_vsl` needs to be set to True in the `train_input` or `eval_input` section of the model config.
`VSLPretrainingTokenGenerator` also uses the config paramaters that are used by `PretrainingTokenGenerator`, in addition to the ones specified below.
| Flag | Default Value | Description |
| --------------- | ------------- | ---------------------------------------------------------------------------------------------- |
| use\_vsl | True | Generate examples with multiple sequences packed together |
| fold\_long\_doc | True | Fold documents larger than max\_seq\_length into multiple sequences, instead of dropping them. |
This section lists down parameters that can be used for `DPOTokenGenerator`.
| Flag | Default Value | Description |
| ------------------- | ------------- | ------------------------------------------------------------------------------------------------------------------------- |
| max\_prompt\_length | 512 | If the sequence exceeds the `max_seq_length`, this parameters caps the prompt length to the specified limit. |
| response\_delimiter | `` | This is used to set the separator between `prompt` and `response`. The user need not set this value for general use-case. |
This section lists down parameters that can be used for `MultiModalPretrainingTokenGenerator`.
| Flag | Default Value | Description |
| -------------- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
| max\_num\_img | 1 | Maximum number of images allowed in one preprocessed sequence. Sequences with more than max\_num\_img images will be discarded |
| num\_patches | None | Number of patches to represent an image. This is determined by the patch-size (in pixels) of the image-encoder, and the pixel count of the input images. |
| is\_multimodal | False | Whether the dataset is multimodal (text plus images) or text only. Set it to True for multimodal tasks. |
This section lists down parameters that can be used for multimodal token generators.
| Flag | Default Value | Description |
| -------------- | ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
| max\_num\_img | 1 | Maximum number of images allowed in one preprocessed sequence. Sequences with more than max\_num\_img images will be discarded |
| num\_patches | 1 | Number of patches to represent an image. This is determined by the patch-size (in pixels) of the image-encoder, and the pixel count of the input images. |
| is\_multimodal | False | Whether the dataset is multimodal (text plus images) or text only. Set it to True for multimodal tasks. |
## Supported Token Generators - Pretraining Mode
* `PretrainingTokenGenerator`: General-purpose pretraining on large text corpora. When `training_objective` is set to `mlm`, it does MLM task processing. For multimodal pretraining, `is_multimodal` is set to True.
* `FIMTokenGenerator`: Designed for fill-in-the-middle tasks. Initialized when `training_objective` is set to `fim` in the config file.
* `VSLPretrainingTokenGenerator`: For visual and language pretraining. Initialized when `use_vsl` is set to `True` in the config file.
## Supported Token Generators - Finetuning Mode
* `FinetuningTokenGenerator`: General-purpose fine-tuning. For multimodal finetuning, `is_multimodal` is set to True.
* `VSLFinetuningTokenGenerator`: Fine-tuning for visual and language tasks. Initialized when `use_vsl` is set to `True` in the config file.
## Other Supported Token Generators
* `DPOTokenGenerator`: Focused on direct preference optimization (DPO) during token generation. Initialized when `mode` is set to `dpo`.
* `NLGTokenGenerator`: Optimized for natural language generation tasks. Initialized when `mode` is set to `nlg`.
## Custom Token Generators
In addition to pre-built token generators, the Model Zoo allows users to implement custom token generators. This enables arbitrary transformations of the input data before tokenization.
To use custom token generators, ensure the configuration file is properly set up. Follow these steps:
**1.** Ensure that the `mode` param is set to `custom`, in order to be able to specify your own token generator.
**2.** Specify the path to the custom token generator class in the config file, in the `token_generator` param, within the `setup` section. This would look like:
```
mode: "custom"
token_generator: ""
```
The `token_generator` path should be specified with the class name being separated with a colon **:** from the module name, for the custom token generator be instantiated correctly.
### Class Implementation Guidelines
The custom token generator must adhere to the following guidelines:
**1.** The constructor’s signature must be as follows:
```python theme={null}
def __init__(
self, params: Dict[str, Any], tokenizer: Any, eos_id: int, pad_id: int
):
"""
Args:
params (Dict[str, Any]): Parameters for the dataset and processing.
tokenizer (Any): Tokenizer to use for tokenization.
eos_id (int): End-of-sequence token ID.
pad_id (int): Padding token ID.
"""
```
**2.** The custom token generator must implement an `encode` method, which tokenizes and encodes the data according to the user definition. For more examples on how the `encode` method looks like, refer to the code of pre-built token generators that are present in Model Zoo.
**3.** The signature of the `encode` method is given below, where it takes in a `semantic_data_array`:
```python theme={null}
def encode(
self, semantic_data_array: List[Dict[str, Any]]
) -> Tuple[Dict[str, Any], Dict[str, int]]:
```
## Conclusion
Configuring token generators is an important step in the preprocessing pipeline for machine learning tasks on Cerebras Systems. By leveraging the comprehensive suite of pre-built token generators provided by Cerebras ModelZoo, you can efficiently handle various stages and tasks in the development of large language models. Additionally, the flexibility to implement custom token generators allows for tailored transformations of input data, meeting specific project requirements.
The introduction of **on-the-fly** data processing further enhances the preprocessing workflow by reducing storage needs and increasing adaptability during training and evaluation. The examples provided for pretraining and fine-tuning configurations illustrate how to set up these processes seamlessly.
Finally, the **TokenFlow** utility offers an invaluable tool for visualizing and debugging preprocessed data, ensuring data integrity and facilitating error detection. By following the guidelines and leveraging the tools outlined in this guide, you can optimize your preprocessing pipeline, leading to more efficient training and improved performance of your machine learning models on Cerebras Systems.