• Stars
    star
    295
  • Rank 135,180 (Top 3 %)
  • Language
    Jupyter Notebook
  • License
    Apache License 2.0
  • Created almost 2 years ago
  • Updated 26 days ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

๐Ÿค— Optimum Intel: Accelerate inference with Intel optimization tools

Optimum Intel

๐Ÿค— Optimum Intel is the interface between the ๐Ÿค— Transformers and Diffusers libraries and the different tools and libraries provided by Intel to accelerate end-to-end pipelines on Intel architectures.

Intel Neural Compressor is an open-source library enabling the usage of the most popular compression techniques such as quantization, pruning and knowledge distillation. It supports automatic accuracy-driven tuning strategies in order for users to easily generate quantized model. The users can easily apply static, dynamic and aware-training quantization approaches while giving an expected accuracy criteria. It also supports different weight pruning techniques enabling the creation of pruned model giving a predefined sparsity target.

OpenVINO is an open-source toolkit that enables high performance inference capabilities for Intel CPUs, GPUs, and special DL inference accelerators (see the full list of supported devices). It is supplied with a set of tools to optimize your models with compression techniques such as quantization, pruning and knowledge distillation. Optimum Intel provides a simple interface to optimize your Transformers and Diffusers models, convert them to the OpenVINO Intermediate Representation (IR) format and run inference using OpenVINO Runtime.

Installation

To install the latest release of ๐Ÿค— Optimum Intel with the corresponding required dependencies, you can use pip as follows:

Accelerator Installation
Intel Neural Compressor python -m pip install "optimum[neural-compressor]"
OpenVINO python -m pip install "optimum[openvino,nncf]"

We recommend creating a virtual environment and upgrading pip with python -m pip install --upgrade pip.

Optimum Intel is a fast-moving project, and you may want to install from source with the following command:

python -m pip install git+https://github.com/huggingface/optimum-intel.git

or to install from source including dependencies:

python -m pip install "optimum-intel[extras]"@git+https://github.com/huggingface/optimum-intel.git

where extras can be one or more of neural-compressor, openvino, nncf.

Quick tour

Neural Compressor

Dynamic quantization can be used through the Optimum command-line interface:

optimum-cli inc quantize --model distilbert-base-cased-distilled-squad --output ./quantized_distilbert

Note that quantization is currently only supported for CPUs (only CPU backends are available), so we will not be utilizing GPUs / CUDA in this example.

To load a quantized model hosted locally or on the ๐Ÿค— hub, you can do as follows :

from optimum.intel import INCModelForSequenceClassification

# Load the PyTorch model hosted on the hub
loaded_model_from_hub = INCModelForSequenceClassification.from_pretrained(
    "Intel/distilbert-base-uncased-finetuned-sst-2-english-int8-dynamic"
)

You can load many more quantized models hosted on the hub under the Intel organization here.

For more details on the supported compression techniques, please refer to the documentation.

OpenVINO

Below are the examples of how to use OpenVINO and its NNCF framework to accelerate inference.

Inference:

To load a model and run inference with OpenVINO Runtime, you can just replace your AutoModelForXxx class with the corresponding OVModelForXxx class. If you want to load a PyTorch checkpoint, set export=True to convert your model to the OpenVINO IR.

- from transformers import AutoModelForSequenceClassification
+ from optimum.intel import OVModelForSequenceClassification
from transformers import AutoTokenizer, pipeline

model_id = "distilbert-base-uncased-finetuned-sst-2-english"
- model = AutoModelForSequenceClassification.from_pretrained(model_id)
+ model = OVModelForSequenceClassification.from_pretrained(model_id, export=True)
tokenizer = AutoTokenizer.from_pretrained(model_id)
cls_pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
text = "He's a dreadful magician."
outputs = cls_pipe(text)

Post-training static quantization:

Post-training static quantization introduces an additional calibration step where data is fed through the network in order to compute the activations quantization parameters. Here is an example on how to apply static quantization on a fine-tuned DistilBERT.

from functools import partial
from optimum.intel import OVQuantizer, OVModelForSequenceClassification
from transformers import AutoTokenizer, AutoModelForSequenceClassification

model_id = "distilbert-base-uncased-finetuned-sst-2-english"
model = AutoModelForSequenceClassification.from_pretrained(model_id)    
tokenizer = AutoTokenizer.from_pretrained(model_id)
def preprocess_fn(examples, tokenizer):
    return tokenizer(
        examples["sentence"], padding=True, truncation=True, max_length=128
    )

quantizer = OVQuantizer.from_pretrained(model)
calibration_dataset = quantizer.get_calibration_dataset(
    "glue",
    dataset_config_name="sst2",
    preprocess_function=partial(preprocess_fn, tokenizer=tokenizer),
    num_samples=100,
    dataset_split="train",
    preprocess_batch=True,
)
# The directory where the quantized model will be saved
save_dir = "nncf_results"
# Apply static quantization and save the resulting model in the OpenVINO IR format
quantizer.quantize(calibration_dataset=calibration_dataset, save_directory=save_dir)
# Load the quantized model
optimized_model = OVModelForSequenceClassification.from_pretrained(save_dir)

Quantization-aware training:

Quantization aware training (QAT) is applied in order to simulate the effects of quantization during training, to alleviate its effects on the modelโ€™s accuracy. Here is an example on how to fine-tune a DistilBERT model on the sst-2 task while applying quantization aware training (QAT).

import evaluate
import numpy as np
from datasets import load_dataset
from transformers import AutoModelForSequenceClassification, AutoTokenizer, TrainingArguments, default_data_collator
- from transformers import Trainer
+ from optimum.intel import OVConfig, OVModelForSequenceClassification, OVTrainer

model_id = "distilbert-base-uncased-finetuned-sst-2-english"
model = AutoModelForSequenceClassification.from_pretrained(model_id)    
tokenizer = AutoTokenizer.from_pretrained(model_id)
dataset = load_dataset("glue", "sst2")
dataset = dataset.map(
    lambda examples: tokenizer(examples["sentence"], padding=True, truncation=True, max_length=128), batched=True
)
metric = evaluate.load("glue", "sst2")
compute_metrics = lambda p: metric.compute(
    predictions=np.argmax(p.predictions, axis=1), references=p.label_ids
)

# The directory where the quantized model will be saved
save_dir = "nncf_results"

# Load the default quantization configuration detailing the quantization we wish to apply
+ ov_config = OVConfig()

- trainer = Trainer(
+ trainer = OVTrainer(
    model=model,
    args=TrainingArguments(save_dir, num_train_epochs=1.0, do_train=True, do_eval=True),
    train_dataset=dataset["train"].select(range(300)),
    eval_dataset=dataset["validation"],
    compute_metrics=compute_metrics,
    tokenizer=tokenizer,
    data_collator=default_data_collator,
+   ov_config=ov_config,
+   task="text-classification",
)
train_result = trainer.train()
metrics = trainer.evaluate()
trainer.save_model()

+ optimized_model = OVModelForSequenceClassification.from_pretrained(save_dir)

You can find more examples in the documentation.

Running the examples

Check out the examples directory to see how ๐Ÿค— Optimum Intel can be used to optimize models and accelerate inference.

Do not forget to install requirements for every example:

cd <example-folder>
pip install -r requirements.txt

More Repositories

1

transformers

๐Ÿค— Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Python
121,026
star
2

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Python
28,073
star
3

diffusers

๐Ÿค— Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
Python
21,823
star
4

datasets

๐Ÿค— The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Python
17,530
star
5

peft

๐Ÿค— PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Python
13,148
star
6

candle

Minimalist ML framework for Rust
Rust
12,686
star
7

tokenizers

๐Ÿ’ฅ Fast State-of-the-Art Tokenizers optimized for Research and Production
Rust
8,286
star
8

trl

Train transformer language models with reinforcement learning.
Python
7,661
star
9

text-generation-inference

Large Language Model Text Generation Inference
Python
7,240
star
10

accelerate

๐Ÿš€ A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Python
6,878
star
11

chat-ui

Open source codebase powering the HuggingChat app
TypeScript
5,586
star
12

deep-rl-class

This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.
MDX
3,541
star
13

alignment-handbook

Robust recipes to align language models with human and AI preferences
Python
3,485
star
14

diffusion-models-class

Materials for the Hugging Face Diffusion Models Course
Jupyter Notebook
3,126
star
15

notebooks

Notebooks using the Hugging Face libraries ๐Ÿค—
Jupyter Notebook
3,114
star
16

distil-whisper

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Python
2,964
star
17

neuralcoref

โœจFast Coreference Resolution in spaCy with Neural Networks
C
2,788
star
18

autotrain-advanced

๐Ÿค— AutoTrain Advanced
Python
2,759
star
19

knockknock

๐ŸšชโœŠKnock Knock: Get notified when your training ends with only two additional lines of code
Python
2,660
star
20

safetensors

Simple, safe way to store and distribute tensors
Python
2,347
star
21

swift-coreml-diffusers

Swift app demonstrating Core ML Stable Diffusion
Swift
2,329
star
22

optimum

๐Ÿš€ Accelerate training and inference of ๐Ÿค— Transformers and ๐Ÿค— Diffusers with easy to use hardware optimization tools
Python
2,086
star
23

awesome-papers

Papers & presentation materials from Hugging Face's internal science day
1,996
star
24

setfit

Efficient few-shot learning with Sentence Transformers
Jupyter Notebook
1,912
star
25

text-embeddings-inference

A blazing fast inference solution for text embeddings models
Rust
1,845
star
26

course

The Hugging Face course on Transformers
MDX
1,832
star
27

evaluate

๐Ÿค— Evaluate: A library for easily evaluating machine learning models and datasets.
Python
1,752
star
28

blog

Public repo for HF blog posts
Jupyter Notebook
1,685
star
29

transfer-learning-conv-ai

๐Ÿฆ„ State-of-the-Art Conversational AI with Transfer Learning
Python
1,654
star
30

swift-coreml-transformers

Swift Core ML 3 implementations of GPT-2, DistilGPT-2, BERT, and DistilBERT for Question answering. Other Transformers coming soon!
Swift
1,543
star
31

pytorch-openai-transformer-lm

๐ŸฅA PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
Python
1,464
star
32

huggingface_hub

All the open source things related to the Hugging Face Hub.
Python
1,311
star
33

Mongoku

๐Ÿ”ฅThe Web-scale GUI for MongoDB
TypeScript
1,277
star
34

hmtl

๐ŸŒŠHMTL: Hierarchical Multi-Task Learning - A State-of-the-Art neural network model for several NLP tasks based on PyTorch and AllenNLP
Python
1,181
star
35

huggingface.js

Utilities to use the Hugging Face Hub API
TypeScript
1,161
star
36

gsplat.js

JavaScript Gaussian Splatting library.
TypeScript
1,114
star
37

llm-vscode

LLM powered development for VSCode
TypeScript
1,060
star
38

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Python
1,033
star
39

pytorch-pretrained-BigGAN

๐Ÿฆ‹A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
Python
986
star
40

torchMoji

๐Ÿ˜‡A pyTorch implementation of the DeepMoji model: state-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc
Python
880
star
41

naacl_transfer_learning_tutorial

Repository of code for the tutorial on Transfer Learning in NLP held at NAACL 2019 in Minneapolis, MN, USA
Python
717
star
42

awesome-huggingface

๐Ÿค— A list of wonderful open-source projects & applications integrated with Hugging Face libraries.
698
star
43

optimum-nvidia

Python
680
star
44

nanotron

Minimalistic large language model 3D-parallelism training
Python
661
star
45

datasets-server

Lightweight web API for visualizing and exploring all types of datasets - computer vision, speech, text, and tabular - stored on the Hugging Face Hub
Python
594
star
46

transformers-bloom-inference

Fast Inference Solutions for BLOOM
Python
546
star
47

pytorch_block_sparse

Fast Block Sparse Matrices for Pytorch
C++
523
star
48

exporters

Export Hugging Face models to Core ML and TensorFlow Lite
Python
518
star
49

llm.nvim

LLM powered development for Neovim
Lua
507
star
50

cookbook

Open-source AI cookbook
Jupyter Notebook
471
star
51

node-question-answering

Fast and production-ready question answering in Node.js
TypeScript
459
star
52

swift-transformers

Swift Package to implement a transformers-like API in Swift
Swift
438
star
53

large_language_model_training_playbook

An open collection of implementation tips, tricks and resources for training large language models
Python
431
star
54

llm-ls

LSP server leveraging LLMs for code completion (and more?)
Rust
416
star
55

llm_training_handbook

An open collection of methodologies to help with successful training of large language models.
Python
385
star
56

tflite-android-transformers

DistilBERT / GPT-2 for on-device inference thanks to TensorFlow Lite with Android demo apps
Java
368
star
57

community-events

Place where folks can contribute to ๐Ÿค— community events
Jupyter Notebook
368
star
58

nn_pruning

Prune a model while finetuning or training.
Jupyter Notebook
360
star
59

swift-chat

Mac app to demonstrate swift-transformers
Swift
346
star
60

speechbox

Python
328
star
61

100-times-faster-nlp

๐Ÿš€100 Times Faster Natural Language Processing in Python - iPython notebook
HTML
325
star
62

education-toolkit

Educational materials for universities
Jupyter Notebook
307
star
63

controlnet_aux

Python
291
star
64

unity-api

C#
284
star
65

open-muse

Open reproduction of MUSE for fast text2image generation.
Python
284
star
66

datablations

Scaling Data-Constrained Language Models
Jupyter Notebook
270
star
67

audio-transformers-course

The Hugging Face Course on Transformers for Audio
MDX
247
star
68

hub-docs

Docs of the Hugging Face Hub
221
star
69

text-clustering

Easily embed, cluster and semantically label text datasets
Python
214
star
70

lighteval

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.
Python
208
star
71

quanto

A pytorch Quantization Toolkit
Python
201
star
72

simulate

๐ŸŽข Creating and sharing simulation environments for embodied and synthetic data research
Python
185
star
73

ratchet

A cross-platform browser ML framework.
Rust
184
star
74

hf_transfer

Rust
181
star
75

instruction-tuned-sd

Code for instruction-tuning Stable Diffusion.
Python
167
star
76

olm-datasets

Pipeline for pulling and processing online language model pretraining data from the web
Python
166
star
77

optimum-neuron

Easy, fast and very cheap training and inference on AWS Trainium and Inferentia chips.
Jupyter Notebook
163
star
78

optimum-benchmark

A unified multi-backend utility for benchmarking Transformers and Diffusers with full support of Optimum's hardware optimizations & quantization schemes.
Python
163
star
79

workshops

Materials for workshops on the Hugging Face ecosystem
Jupyter Notebook
143
star
80

OBELICS

Code used for the creation of OBELICS, an open, massive and curated collection of interleaved image-text web documents, containing 141M documents, 115B text tokens and 353M images.
Python
142
star
81

cosmopedia

Python
138
star
82

api-inference-community

Python
131
star
83

diffusion-fast

Faster generation with text-to-image diffusion models.
Python
127
star
84

sharp-transformers

A Unity plugin for using Transformers models in Unity.
C#
104
star
85

llm-swarm

Manage scalable open LLM inference endpoints in Slurm clusters
Python
104
star
86

competitions

Python
98
star
87

optimum-habana

Easy and lightning fast training of ๐Ÿค— Transformers on Habana Gaudi processor (HPU)
Python
98
star
88

hf-hub

Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package
Rust
93
star
89

olm-training

Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.
Python
87
star
90

fuego

[WIP] A ๐Ÿ”ฅ interface for running code in the cloud
Python
84
star
91

tune

Python
83
star
92

datasets-viewer

Viewer for the ๐Ÿค— datasets library.
Python
82
star
93

optimum-graphcore

Blazing fast training of ๐Ÿค— Transformers on Graphcore IPUs
Python
78
star
94

frp

FRP Fork
Go
73
star
95

paper-style-guide

71
star
96

block_movement_pruning

Block Sparse movement pruning
Python
70
star
97

data-measurements-tool

Developing tools to automatically analyze datasets
Python
69
star
98

amused

Python
68
star
99

doc-builder

The package used to build the documentation of our Hugging Face repos
Python
67
star
100

hfapi

Simple Python client for the Hugging Face Inference API
Python
66
star