talkdatatomee's profile picture. #DataScience, #Statistics, #R, #Python #DataViz #MachineLearning #DeepLearning even #MLOps

Talk Data to Me

@talkdatatomee

#DataScience, #Statistics, #R, #Python #DataViz #MachineLearning #DeepLearning even #MLOps

Talk Data to Me 已轉發

XGBoost for Regression, Predictive Modeling, and Time Series Analysis — Learn how to build, evaluate, & deploy predictive models: amzn.to/4l2YcU9 v/ @PacktDataML — My review: 🟠XGBoost is definitely the focal point and central contribution of this book, and also those…

KirkDBorne's tweet image. XGBoost for Regression, Predictive Modeling, and Time Series Analysis — Learn how to build, evaluate, & deploy predictive models: amzn.to/4l2YcU9 v/ @PacktDataML
—
My review:

🟠XGBoost is definitely the focal point and central contribution of this book, and also those…

Talk Data to Me 已轉發

Search OPENAI_API_KEY on GitHub and thank Vibe Coders.


Talk Data to Me 已轉發

Microservice Roadmap

PythonPr's tweet image. Microservice Roadmap

Talk Data to Me 已轉發

🚨NEW: Python library for LLM Prompt Management This is what it does:

mdancho84's tweet image. 🚨NEW: Python library for LLM Prompt Management

This is what it does:

Talk Data to Me 已轉發

framework for domain-specific knowledge extraction and reasoning with LLMs

tom_doerr's tweet image. framework for domain-specific knowledge extraction and reasoning with LLMs

Talk Data to Me 已轉發

Yup

MathMatize's tweet image. Yup

Talk Data to Me 已轉發

How Small Are Microplastics? We Put Things Into Perspective 🔬 visualcapitalist.com/how-small-are-…

VisualCap's tweet image. How Small Are Microplastics? We Put Things Into Perspective 🔬

visualcapitalist.com/how-small-are-…

Talk Data to Me 已轉發
miniapeur's tweet image.

Talk Data to Me 已轉發

This should be impossible! You can clean any ML dataset in just three lines of code. Flag outliers, find label errors, and more, across: - Any data (tabular, text, image, etc.) - Any task (classification, entity recognition, etc.) 100% open-source, built by MIT researchers.

_avichawla's tweet image. This should be impossible!

You can clean any ML dataset in just three lines of code. Flag outliers, find label errors, and more, across:

- Any data (tabular, text, image, etc.)
- Any task (classification, entity recognition, etc.)

100% open-source, built by MIT researchers.

Talk Data to Me 已轉發

Most "agents" today are shallow while loops around an LLM and tools. Works for simple tasks, but fails when a task requires 50+ steps over several days. To solve complex problems, we need an architectural shift towards Deep Agents (Agents 2.0). We have to decouple planning…

_philschmid's tweet image. Most "agents" today are shallow while loops around an LLM and tools. Works for simple tasks, but fails when a task requires 50+ steps over several days.

To solve complex problems, we need an architectural shift towards Deep Agents (Agents 2.0). 

We have to decouple planning…

Talk Data to Me 已轉發

The Transformer's encoder clearly explained 👇🏻

rfeers's tweet image. The Transformer's encoder clearly explained 👇🏻

Talk Data to Me 已轉發

Visualized: H-1B Visa Approvals by Country in 2024 🛂 visualcapitalist.com/visualized-h-1…

VisualCap's tweet image. Visualized: H-1B Visa Approvals by Country in 2024 🛂

visualcapitalist.com/visualized-h-1…

Talk Data to Me 已轉發

What is CI/CD

sahnlam's tweet image. What is CI/CD

Talk Data to Me 已轉發

RAG - Retrieval Augmented Generation

PythonPr's tweet image. RAG - Retrieval Augmented Generation

Talk Data to Me 已轉發

Multi-Head Latent Attention 🔗 github.com/rasbt/LLMs-fro…

rasbt's tweet image. Multi-Head Latent Attention
🔗 github.com/rasbt/LLMs-fro…

Just a bit of weekend coding fun: A memory estimator to calculate the savings when using grouped-query attention vs multi-head attention (+ code implementations of course). 🔗 github.com/rasbt/LLMs-fro… Will add this for multi-head latent, sliding, and sparse attention as well.

rasbt's tweet image. Just a bit of weekend coding fun: A memory estimator to calculate the savings when using grouped-query attention vs multi-head attention (+ code implementations of course).

🔗 github.com/rasbt/LLMs-fro…

Will add this for multi-head latent, sliding, and sparse attention as well.


Talk Data to Me 已轉發

PyCaret is an open-source, low-code machine learning library in Python designed to simplify and automate workflows for building, training, and deploying machine learning models. Supporting tasks like classification, regression, clustering, and time-series forecasting, PyCaret…

JoachimSchork's tweet image. PyCaret is an open-source, low-code machine learning library in Python designed to simplify and automate workflows for building, training, and deploying machine learning models. Supporting tasks like classification, regression, clustering, and time-series forecasting, PyCaret…

Talk Data to Me 已轉發

Here's FastAPI 0.119.0 🚀 With support for both @pydantic v2 and v1 on the same app, at the same time 🤯 This is just so you can migrate to Pydantic v2 if you haven't done it yet, here's your (last) chance! 🤓 Pydantic v1 is now deprecated ⛔️ Read more fastapi.tiangolo.com/how-to/migrate…

FastAPI's tweet image. Here's FastAPI 0.119.0 🚀

With support for both @pydantic v2 and v1 on the same app, at the same time 🤯

This is just so you can migrate to Pydantic v2 if you haven't done it yet, here's your (last) chance! 🤓

Pydantic v1 is now deprecated ⛔️

Read more fastapi.tiangolo.com/how-to/migrate…

Talk Data to Me 已轉發
e507's tweet image.

Talk Data to Me 已轉發

Top 10 Python Libraries for Generative AI You Need to Master in 2025 (The tools behind document agents, intelligent assistants, and next-gen interfaces.) Everything you need to know: 🧵

mdancho84's tweet image. Top 10 Python Libraries for Generative AI You Need to Master in 2025

(The tools behind document agents, intelligent assistants, and next-gen interfaces.)

Everything you need to know: 🧵

Talk Data to Me 已轉發

Me after seeing the first slides I made when I joined consulting

consultingcmdy's tweet image. Me after seeing the first slides I made when I joined consulting

Loading...

Something went wrong.


Something went wrong.