Derrick Mwiti
@_mwitiderrick
Followers
6,665
Following
475
Media
405
Statuses
7,360
Tweets on machine learning and deep learning Writes
Remote
Joined June 2013
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
Hamas
• 924064 Tweets
#NXTNoMercy
• 84114 Tweets
ESPN
• 73635 Tweets
YouTube TV
• 58041 Tweets
Dinamarca
• 49939 Tweets
Big 10
• 35792 Tweets
Giulia
• 34639 Tweets
Falcao
• 24855 Tweets
Q33 U STEAL MY HEART
• 22293 Tweets
DirecTV
• 20982 Tweets
Roxanne
• 17774 Tweets
Hudson
• 17538 Tweets
Braves
• 16569 Tweets
MIX師
• 15850 Tweets
Grant Justice
• 15084 Tweets
Trojans
• 10987 Tweets
Lacy
• 10953 Tweets
解雇規制緩和
• 10692 Tweets
Jaida
• 10498 Tweets
Python, NumPy, Pandas, Matplotlib, Scikit-learn, and TensorFlow are FUNDAMENTAL skills for anyone learning data science and machine learning.
Master them tuning with these FREE resources.
37
618
2K
Python, NumPy, Pandas, Matplotlib, Scikit-learn, and TensorFlow are FUNDAMENTAL data science and machine learning skills.
Master them with these FREE resources.
23
378
2K
Machine Learning Tools 🤖
Development
• PyCharm
• VScode
• Jupyter
Training
• PyTorch Lightning
• Scikit-Learn
• TensorFlow
• LightGBM
• XGBoost
• PyTorch
Tuning
• Keras tuner
• Hyperopt
• Optuna
Optimization
• SparseML
Deployment / Packaging
• Hugging Face
38
502
2K
Python, NumPy, Pandas, Matplotlib, Scikit-learn, and TensorFlow are FUNDAMENTAL skills for anyone learning data science and machine learning.
Master them tuning with these FREE resources:
15
282
1K
I started my career in machine learning back in 2017.
Here are the 5 COURSES I took :
27
314
1K
Python, NumPy, Pandas, Matplotlib, and Scikit-learn are FUNDAMENTAL skills for anyone learning data science and machine learning 🤖
Master them tuning with these FREE resources 🔥
A Thread 🧵👇
25
255
994
I started my career in data science and machine learning back in 2017 ⏳
I wrote a book on how to build a career as a technical writer in DS/ML✨
Today is my birthday, and I am giving the book for FREE 🎂
To receive:
• Like, comment "Send"
• Must be following so I can DM
648
89
911
I started my career in machine learning back in 2017⌛️
Here are the 5 COURSES I took ✨:
--A Thread--
🔥
34
201
649
Coursera is an amazing resource for learning data science and machine learning.
Here are 4 amazing courses I have taken from Coursera:
6
103
614
4 amazing books for data science and machine learning 🤖
1️⃣ Building Machine Learning Powered Applications
2️⃣ Practical Machine Learning for Computer Vision
3️⃣ Building Machine Learning Pipelines
4️⃣ Desginig Machine Learing Sytems
Check them out 👇🏻
12
131
545
Fine-tuning a Llama 65B parameter model requires 780 GB of GPU memory.
This kind of compute is outside the purview of most individuals.
Thanks to parameter-efficient fine-tuning strategies, it is now possible to fine-tune a 7B parameter model on a single GPU, like the one
20
95
540
Coursera is an amazing resource for learning data science and machine learning 🤖
Here are 4 amazing courses I have taken from Coursera🔥
--A Thread--
🧵
14
109
503
Detecting small objects with computer vision models is challenging.
This is because they occupy a few pixels in the entire image.
However, the SAHI technique makes it possible to detect small objects using various models such as YOLOv5.
SAHI is a generic slicing-aided
18
91
518
I have been working in machine learning remotely since 2017.
Here is a blueprint for getting remote ML jobs again and again (proven strategy):
13
89
424
I started my career in data science and machine learning back in 2017 ⏳
Here is a 5-STEP roadmap to get started in 2024:
8
115
413
Kaggle is an amazing resource, particularly for someone learning data science and machine learning 🛠
Here's how I have used Kaggle to advance my career 🔥
7
100
397
The Transformer architecture implemented from scratch in TensorFlow.
Let me break it down for you:
8
58
321
Google recently released an alternative to NumPy that's way faster for numerical computation; JAX 👾
They also shipped a deep learning library for JAX called Flax 🤖
Master JAX and Flax with these 12 FREE resources 🔥
--A Thread--
🧵
17
108
306
In 2022, I wrote two books.
Feel exhilarating to hold the printed versions.
#datascience
#writing
#machinelearning
20
41
291
Kaggle is an amazing resource, particularly for someone learning data science and machine learning.
Here's how you can use Kaggle to advance your career:
5
45
284
Training machine models locally is limited to the computation power of your computer.
Here are 6 alternatives for training ML models that will give you more computational resources, including GPUs for FREE:
9
51
276
I started my career in machine learning back in 2017 ⌛️
Here are 5 critical skills for landing a job in the industry ✨
--A Thread--
🧵
11
61
276
Google JAX is faster than NumPy for numerical computation.
Master JAX with these 12 FREE resources:
11
46
278
Training NLP and CV models from scratch is a waste of resources.
Instead, apply transfer learning using pre-trained models.
Here's how transfer learning works in 6 steps.
--A Thread--
🧵
13
63
270
Training NLP and CV models from scratch is a waste of resources.
Instead, apply transfer learning using pre-trained models.
Here's how transfer learning works in 6 steps:
3
54
249
Kaggle is an amazing resource, particularly for someone learning data science and machine learning 🛠
Here's how I have used Kaggle to advance my career 🔥
--A Thread--
🧵
1/3
11
43
234
Attending Google IO Connect in Amsterdam.
So many insightful sessions on machine learning from the best from Google.
13
10
233
I just discovered this completely open-source computer science degree from Open Source Society University
6
59
228
I have been writing data science and ML content for ~ 8 years now.
Technical writing can accelerate your career as an ML practitioner.
Here are 15 principles to follow when writing technical content.
4
27
142
I started my career in data science and machine learning back in 2017 ⏳
Wrote 3 books to get you started 🔥
Get them for FREE:
--A Thread--
🧵
11
58
228
The Transformer architecture implemented from scratch using TensorFlow 🔥
Let me break it down for you in this thread:
🧵👇
10
41
225
I started my career in data science and machine learning back in 2017 ⏳
Here is a 5 STEP roadmap to get started in 2023 🔥
--A Thread--
🧵
10
85
214
I started my career in machine learning back in 2017 ⌛️
Started by learning TensorFlow 🤖
Master TensorFlow with these 11 FREE resources 🔥
--A Thread--
🧵
20
78
200
Counting cars on a CPU with YOLOv5, Supervision, and DeepSparse
10
40
202
Training an ML model inside a Jupyter notebook is something every data scientist knows.
But do you know how to debug your code using IDEs?
If the answer is NO, this post is for you:
8
36
195
I started my career in machine learning back in 2017.
Started by learning TensorFlow.
Master TensorFlow with these 11 FREE resources:
6
46
185
Tensors are a FUNDAMENTAL concept in machine learning.
Master them with this FREE resource, covering:
• What is a Tensor?
• How to create tensors
• Functions to create various Tensor objects
• How to create tensors with custom values
• How to initialize tensors with
7
34
187
Run a medical chatbot on CPUs, no GPUs required.
Here's how:
This video walks you through running a medical chatbot using open-source LLMs such as Llama on your computer without GPUs.
The application uses DeepSparse by
@neuralmagic
for accelerated inference on CPUs, LangChain,
6
38
181
Training an ML model inside a Jupyter notebook is something every data scientist knows 🏋️
But do you know how to debug your code using IDEs?
If the answer is NO, this thread is for you 🔥
🧵
1/6
10
36
177
How to deploy NLP and computer vision models on Google Cloud.
Pre-trained CV and NLP models offer good accuracy because they are trained on massive datasets.
Unfortunately, these models are very large, making them difficult and expensive to deploy. Due to their size, they
5
41
177
Training machine models locally is limited to the computation power of your computer.
Here are 6 alternatives for training ML models that will give your more computational resources, including GPUs:
9
55
175
The most common large language model evaluation metrics:
• Perplexity
• BLEU
• ROUGE
• BERTScore
• COMET
• METEOR
• BLEURT
• GPTScore
• PRISM
• BARTScore
• G-Eval
• Human Evaluation
Details below:
Perplexity measures how good a model is at predicting the
9
29
155
Google JAX is faster than NumPy for numerical computation.
Flax is the deep learning library built on top of JA.
Master JAX and Flax with these 12 FREE resources.
7
41
154
Training machine learning models is only 5% of the work required to build production-grade systems.
Discover the other 95% in this thread 🔥
13
40
148
Machine learning platforms
Training
• Paperspace Gradient
• Kaggle Notebooks
• Google Colab
• Saturn Cloud
• SageMaker
• activeloop
• Anaconda
• Deepnote
• Roboflow
• Vertex AI
• Spell
• H2O
Optimization
• Sparsify by
@neuralmagic
Observability
• Deepchecks
•
5
45
147
Top BLOGS to learn Data Science and Machine Learning 🚀
A thread 🧵👇🏻
4
34
147
Interested in landing a remote role in machine learning?
Been working remotely since 2018.
Use these steps:
9
16
143
You are still deploying ML models on GPUs?
Well, you got some money to throw away.
Use CPUs for a 66% reduction in inference cost without loss of performance, in fact, with 2X better performance than a T4 GPU on a 4-core CPU laptop 🔥.
Here's how in 3 steps:
--A Thread--
🧵
8
15
140
I removed 50% of the weights from a top leaderboard LLM without negatively impacting the evals.
Using SparseML from
@neuralmagic
I was able to zero out 50% of the SOLAR-10.7B-Instruct-v1.0 weights.
I then quantized the remaining weights to INT8.
The results are amazing!
7
28
141
Knowing how to DEPLOY models is almost mandatory to land a job in machine learning.
Master how to deploy models on AWS with these 3 FREE resources:
4
40
136
You can now run our popular sparse LLM HF Space locally.
No GPU required, just plain old CPUs
4
25
132
I started my career in data science and machine learning back in 2017 🕰
Learning multiple concepts and technologies is critical when starting your journey 🤖
To help you get started, I have curated various resources as PDFs 📑
Download them for free from the next tweet 🔥
9
26
133
Knowing how to DEPLOY models is almost mandatory to land a job in machine learning 🏗
Master how to deploy models on AWS with these 3 FREE resources 🔥
--A Thread--
🧵
9
34
127
Context length is one of the biggest problems with LLMs such as ChatGPT.
There is a limitation on the number of words in your prompt because the models can only accept a certain number of tokens.
The solution? Embeddings.
Word embedding is a technique used to represent
5
24
124
I started my career in machine learning back in 2017⌛️
Here's a detailed roadmap to learn machine learning in 2023✨
-- A Thread --
🧵
5
29
121
I wrote my first data science article in 2018.
Now written over 300 data science and ML articles.
I think you, too, should document your learnings.
If that sounds like something you’d like to pursue, I’d like to offer an ULTIMATE guide for doing so.
👇🏻
7
21
117
You use CPUs and GPUs to deploy ML models every day.
But have you ever considered how they work in machine learning?
Here's how they differ and why you should choose a CPU over a GPU for your next deployment.
--A Thread--
🧵
6
22
116
I started my career in data science and machine learning back in 2017 ⏳
Still amazes me that a $9 dollar data science course can change your life ✨
Here are the 3 courses I took when getting started🔥
--A Thread--
🧵
5
22
116
Porting YOLO to PyTorch from DarkNet was a game changer in the computer vision world.
YOLOv5 is arguably the most popular object detection model today, as a result.
However, deploying it for real-time inference will still require reducing its size.
There are 2 strategies for
10
21
107
Are you still deploying uncompressed ML models in 2023?
STOP.
Apply Gradual Magnitude Pruning (GMP), the current KING in ML model pruning, to reduce the size of large models by 20X without loss of accuracy.
Here's how to apply GMP in 5 steps.
--A Thread--
🧵
6
17
107
Smaller machine learning models are vital for deployment, particularly for real-time inference and on-edge devices.
Reducing the size of the model also leads to lower deployment costs.
There are 3 main techniques that you can use to reduce the size of an ML model. They are:
9
18
105
Medical school is 5 years ⚕️
Law school 7 years 🧳
Don't stop learning data science and ML after a few months.
9
14
99
Training NLP and CV models from scratch is a waste of resources ❌
Instead, apply transfer learning using pre-trained models 🤖
Here's how transfer learning works in 6 steps 🪜
--A Thread--
🧵
5
18
95
The model you have on your laptop doesn't help anyone.
You have to deploy it for people to get value out of it.
Enter MLOps.
Here's everything you need to know about MLOps.
4
14
90
GPUs are becoming scarce.
Everyone is now training and deploying ML models 🦾
Deploy your ML models on CPUs with the same performance as a T4 GPU.
Here's how 🔥
--A Thread--
🧵
1/6
9
19
96
The model you have on your laptop 💻 doesn't help anyone.
You have to deploy it for people to get value out of it.
Enter MLOps.
Here's everything you need to know about MLOps.
--A Thread--
🧵
11
19
91
Machine learning projects can fail due to a myriad of reasons.
Here are the top 5 mistakes that lead to ML project failure and how to avoid them, according to Dr. Michael Lones.
6
15
89
I removed 50% of the weights from a top leaderboard LLM without negatively impacting the evals.
Using SparseML from
@neuralmagic
I was able to zero out 50% of the SOLAR-10.7B-Instruct-v1.0 weights.
I then quantized the remaining weights to INT8.
The results are amazing!
10
16
89
I have been writing data science and ML content for ~ 8 years now 🕧
Technical writing can accelerate your career as an ML practitioner 🤖
Here are 15 principles to follow when writing technical content ✍️
--A Thread--
🧵
12
25
84
Python for data science tutorial
Master Python using this complete guide with examples and a notebook.
1
6
84
I wrote my first data science article in 2018.
Now written over 300 data science and ML articles.
I think you, too, should document your learnings.
If that sounds like something you’d like to pursue, I’d like to offer an ULTIMATE guide for doing so.
4
12
82
I started my career in machine learning back in 2017⌛️
Here are THREE things I did to get my first $300 gig ✨
--A Thread--
🔥
10
15
83
Training machine learning models is only 5% of the work required to build production-grade systems.
Discover the other 95%:
5
18
79
There are various steps taken when building machine learning models.
For instance, data pre-processing, model development, and fine-tuning the model, to mention a few.
These steps generate some information such as:
• Model parameters
• Model versions
• Data set versions
6
13
75
GPUs have scarce.
Everyone is now training and deploying ML models.
Deploy your ML models on CPUs with the same performance as a T4 GPU.
Here's how:
5
15
73
1️⃣ Python for Data Science and Machine Learning Bootcamp
Learn how to use NumPy, Pandas, Seaborn , Matplotlib , Plotly , Scikit-Learn , Machine Learning, Tensorflow , and more!
1
22
72
Can one data science article change your life?
On the 18th of Feb 2018, I published an article that changed the trajectory of my career.
Here is the story:
2
8
67
What are logits in deep learning?
Logits are the outputs of a neural network before the activation function is applied. They are the unnormalized probabilities of the item belonging to a certain class.
Logits are often used in classification tasks, where the goal is to predict
11
8
72
Technical Writing 101 for machine learning professionals:
Over the past 5 years, I have written over 200 ML blog posts for machine learning companies.
Want to know the secret?
Here's the ultimate guide:
6
16
68
Neural networks learn by reducing the loss function during training.
Discover how a loss function helps the network learn:
2
11
65
Accelerate your NLP pipelines with sparse transformers 🤖
You can get a 3X CPU performance increase by optimizing your models with only a few lines of code 🔥
--A Thread--
🧵
1/3
7
10
67
Object detection on a CPU using Supervision from
@roboflow
and DeepSparse from
@neuralmagic
.
Supervision provides the tools to reduce repetitive work in building computer vision applications, such as creating zones, annotating, and tracking objects.
DeepSparse provides
6
5
65
Building ML models is cool🤖.
But you are set to fail if you rush to algorithms too quickly.
Here are 5 things you should do before you start to build models🔥:
--A Thread--
🧵
7
18
66
O’Reilly has the best books in AI/machine learning.
Here are 4 books to include on your shelf if you are interested in building machine learning powered applications.
9
11
64
Tom is one of 263 Kaggle Competition Grandmasters.
He has participated in over 40 competitions on Kaggle.
He reveals how he got started and the process he uses when competing on Kaggle.
Tom, as he is popularly known on Kaggle, also reveals what you need to do to earn the
1
12
68
You are still deploying ML models on GPUs?
Well, you got some money to throw away.
Use CPUs for a 66% reduction in inference cost without loss of performance, in fact, with 2X better performance than a T4 GPU on a 4-core CPU laptop 🔥.
Here's how in 3 steps:
--A Thread--
🧵
4
17
65
Deploying large language models on CPU is now a viable option.
This is a result of the work of researchers from
@neuralmagic
and
@ISTAustria
.
For example, the demo in the video below is running on CPU on
@huggingface
Space.
In their latest paper, they successfully applied
8
18
65
We sparse fine-tuned Llama 2 7B to run on CPUs only, no GPU.
Here are the technical details (and demo):
In sparse-fine tuning Llama 2, we focused on the GSM8k dataset like in the MPT setup.
Llama 2 achieves 0% zero-shot accuracy on this task without any fine-tuning.
5
16
63
Machine learning is one of the hottest topics of the past decade.
Needless to say that it is being applied in all industries.
Follow me
@themwiti
for daily ML content:
• Technical deep dives
• Resources
• MLOps
• Tools
• NLP
• CV
Here is some of my best work:
4
7
61
Building machine learning models is an experimental process that requires several iterations.
You change different model parameters or data preprocessing steps at each iteration to obtain an optimal model.
It is vital to keep track of the processing steps and the parameters at
7
14
64
Everything you use today is powered by machine learning🚀.
Even this tweet was recommended to you by an ML algorithm🔥.
But do you know where ML came from?
Here's the story of how ML came into the world 🌎.
--A Thread--
🧵
7
10
63
Are you still deploying uncompressed ML models in 2023?
STOP.
Apply Gradual Magnitude Pruning (GMP), the current KING in ML model pruning, to reduce the size of large models by 20X without loss of accuracy.
Here's how to apply GMP in 5 steps 🔥
--A Thread--
🧵
7
15
61
Optimizing ML models for deployment is not an option ❌
Particularly for enterprises that want to lower their computing costs while improving production performance 💸
Consider these three model optimization techniques before deploying your next model 🦾
--A Thread--
🧵
1/3
9
9
62
A vector database.
The coolest kid on the block due to advancements in large language models.
Here's what it is and why you need to be using one:
3
15
62
Technical writing is a massive asset for any machine learning professional.
I have written over 200 articles in the last 6 years.
Here's how to leverage writing to land jobs, even if you have never written a single blog post before:
5
14
62
Technical writing is an art anyone can master.
Here are 3 of the best FREE resources to sharpen your skills (in no time):
1
10
60
1️⃣ Python for Data Science and Machine Learning Bootcamp
Learn how to use NumPy, Pandas, Seaborn , Matplotlib , Plotly , Scikit-Learn , Machine Learning, Tensorflow , and more!
3
10
58