mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-06-24 09:21:18 +08:00
Examples in the MLX framework
46da74fea2
* Unify attention mask creation in LLMs.
Currently, each model implementation in `mlx-examples/llms/models` has ad-hoc
code to create a mask for the attention mechanism. This usually takes the form:
```
mask = None
if h.shape[1] > 1:
mask = nn.MultiHeadAttention.create_additive_causal_mask(h.shape[1])
mask = mask.astype(h.dtype)
```
This correctly creates a mask only if the input consists of more than one token.
But this code assumes the multi-token input is at the beginning of inference.
If, for example, we are evaluating multiple tokens because of speculative
decoding or prompt cache reuse, this mask will not have the correct shape and
and will cause the raising of an exception in the attention computation.
Some of the models correctly implement the mask creation with code like this:
```
mask = None
if h.shape[1] > 1:
mask = create_additive_causal_mask(
h.shape[1], cache[0].offset if cache is not None else 0
)
mask = mask.astype(h.dtype)
```
This commit unifies the attention mask creation for all models with a new
function `create_attention_mask`, reducing code duplication and helping all
models support inference performance enhancements like those mentioned above.
* Allow batches in LLM key-value cache
The current implementation of the LLM key-value cache assumes that
the input batch is of size 1. Input batching (evaluating multiple
alterative inputs at the same time) can be a valuable tool for
speculative sampling and other techniques.
This change removes the hard-coded batch size from the code that
resizes the key-value cache.
* Simplify causal mask creation
Use the same codepath regardless of whether there's an offset or
not. Addresses [this comment](https://github.com/ml-explore/mlx-examples/pull/911#discussion_r1691459717).
* Use old-style type annotation to avoid linter error
|
||
|---|---|---|
| .circleci | ||
| bert | ||
| cifar | ||
| clip | ||
| cvae | ||
| gcn | ||
| llava | ||
| llms | ||
| lora | ||
| mnist | ||
| normalizing_flow | ||
| segment_anything | ||
| speechcommands | ||
| stable_diffusion | ||
| t5 | ||
| transformer_lm | ||
| whisper | ||
| .gitignore | ||
| .pre-commit-config.yaml | ||
| ACKNOWLEDGMENTS.md | ||
| CODE_OF_CONDUCT.md | ||
| CONTRIBUTING.md | ||
| LICENSE | ||
| README.md | ||
MLX Examples
This repo contains a variety of standalone examples using the MLX framework.
The MNIST example is a good starting point to learn how to use MLX.
Some more useful examples are listed below.
Text Models
- MLX LM a package for LLM text generation, fine-tuning, and more.
- Transformer language model training.
- Minimal examples of large scale text generation with LLaMA, Mistral, and more in the LLMs directory.
- A mixture-of-experts (MoE) language model with Mixtral 8x7B.
- Parameter efficient fine-tuning with LoRA or QLoRA.
- Text-to-text multi-task Transformers with T5.
- Bidirectional language understanding with BERT.
Image Models
- Image classification using ResNets on CIFAR-10.
- Generating images with Stable Diffusion or SDXL.
- Convolutional variational autoencoder (CVAE) on MNIST.
Audio Models
- Speech recognition with OpenAI's Whisper.
Multimodal models
Other Models
- Semi-supervised learning on graph-structured data with GCN.
- Real NVP normalizing flow for density estimation and sampling.
Hugging Face
Note: You can now directly download a few converted checkpoints from the MLX Community organization on Hugging Face. We encourage you to join the community and contribute new models.
Contributing
We are grateful for all of our contributors. If you contribute to MLX Examples and wish to be acknowledged, please add your name to the list in your pull request.
Citing MLX Examples
The MLX software suite was initially developed with equal contribution by Awni Hannun, Jagrit Digani, Angelos Katharopoulos, and Ronan Collobert. If you find MLX Examples useful in your research and wish to cite it, please use the following BibTex entry:
@software{mlx2023,
author = {Awni Hannun and Jagrit Digani and Angelos Katharopoulos and Ronan Collobert},
title = {{MLX}: Efficient and flexible machine learning on Apple silicon},
url = {https://github.com/ml-explore},
version = {0.0},
year = {2023},
}