Nibaldo @CyberMath4

Tweets

1K
Followers

104
Following

1K
Likes

2K

ollama @ollama

a month ago

.@OpenAI has been cooking! Here is OpenAI's Ollama cookbook cookbook.openai.com/articles/gpt-o…

28 187 1K 74K 471

ℏεsam @Hesamation

a month ago

Vibe-coded AI startup 2025

108 2K 17K 885K 3K

Download Image

This is the fastest serving engine for LLMs! LMCache cuts time-to-first-token by 7x and slashes GPU costs dramatically. Think of it as a smart caching layer that remembers everything your LLM has processed before. 100% open-source, makes vLLM go brr...

22 182 1K 76K 1K

Download Image

Sebastian Raschka @rasbt

a month ago

So, I did some coding this week... - Qwen3 Coder Flash (30B-A3B) - Mixture-of-Experts setup with 128 experts, 8 active per token - In pure PyTorch (optimized for human readability) - in a standalone Jupyter notebook - Runs on a single A100

32 283 2K 136K 2K

Download Image

Google Gemini App @GeminiApp

a month ago

The wait is over: Deep Think is here. At I/O, we previewed the frontiers of Gemini’s thinking capabilities. Now, @Google AI Ultra subscribers can experience it in the Gemini app. With Deep Think, Gemini 2.5 is able to intelligently extend its "thinking time" so it can generate…

191 459 3K 464K 605

Download Video

DATO PROTEGIDO ⛩ (hazzim.bsky.social) @HazzimIO

a month ago

DevOps life.

7 247 2K 78K 324

Download Image

MIT CSAIL @MIT_CSAIL

2 months ago

A free MIT guide to key computer vision concepts: bit.ly/43Tn1vW

8 197 849 45K 669

Download Image

Nina @HeyNina101

3 months ago

Don’t let your AI project die in a notebook. You don’t need more features. You need structure. This is the folder setup that actually ships from day one. 📁 𝗧𝗵𝗲 𝗳𝗼𝗹𝗱𝗲𝗿 𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲 𝘁𝗵𝗮𝘁 𝘄𝗼𝗿𝗸𝘀 Forget monolithic scripts. You need this: /config 🔹YAML…

10 163 851 83K 2K

Download Image

Bindu Reddy @bindureddy

5 months ago

A Great Cover For A Vibe Coding Book 😆

34 336 2K 201K 485

Download Image

Akshay 🚀 @akshay_pachaar

6 months ago

5 techniques to fine-tune LLMs, explained visually! Fine-tuning large language models traditionally involved adjusting billions of parameters, demanding significant computational power and resources. However, the development of some innovative methods have transformed this…

9 205 869 66K 874

Download Gif

Unsloth AI @UnslothAI

6 months ago

We made a Guide to teach you how to Fine-tune LLMs correctly! Learn about: • Choosing the right parameters & training method • RL, GRPO, DPO & CPT • Data prep, Overfitting & Evaluation • Training with Unsloth & deploy on vLLM, Ollama, Open WebUI 🔗 docs.unsloth.ai/get-started/fi…

29 350 2K 93K 2K

Download Image

DeepSeek @deepseek_ai

7 months ago

🚀 Day 0: Warming up for #OpenSourceWeek! We're a tiny team @deepseek_ai exploring AGI. Starting next week, we'll be open-sourcing 5 repos, sharing our small but sincere progress with full transparency. These humble building blocks in our online service have been documented,…

1K 3K 21K 2.5M 2K

𝑽𝒂𝒍𝒆𝒓𝑰𝑨 @ValeriA_Tech

7 months ago

🚨 Mientras todos miraban a Trump y Putin, Microsoft creó un nuevo estado de la materia. Esto lo cambia TODO. Te cuento lo más importante sobre el chip cuántico Majorana 1 de Microsoft 🧵👇

71 860 4K 605K 2K

Download Image

Nicéphore @nicephore_ai

7 months ago

130 years ago, the Lumière brothers gave birth to one of the greatest inventions of all times... On a very peculiar evening at the Grand Café, light was made alive ✨ Our AI short "1895" is a tribute to the rich history of the 7th art and a reflection on its evolution in the…

25 140 653 30K 389

Download Video

Philipp Schmid @_philschmid

7 months ago

SFT Memorizes, RL Generalizes. New Paper from @GoogleDeepMind shows that Reinforcement Learning generalizes at cross-domain, while SFT primarily memorizes. rule-based tasks, while SFT memorizes the training rule. 👀 Experiments 1️⃣ Model & Tasks: Llama-3.2-Vision-11B;…

15 174 969 95K 868

Download Image

𝐒𝐫𝐢𝐧𝐢𝐯𝐚𝐬𝐚 𝐑𝐚𝐠𝐡𝐚𝐯𝐚 ζ(1/2 + i σₙ )=0 @SrinivasR1729

8 months ago

Hi, Wishing you a radiant start to the year 2025. May it be filled with unbounded possibilities, integrals of success, and exponential growth in every endeavor. Just like a blank canvas waiting for your creative proofs, let’s keep exploring new theorems, summing our shared…

0 159 903 44K 233

Download Image

Technology and Businesses @TechnoNBusiness

9 months ago

Business strategy is the roadmap for achieving organizational objectives, involving resource allocation, market analysis, and value creation to navigate competitive landscapes effectively. Here are the three layers. #Strategy #Business #Entrepreneurship

2 4 17 406 5

Download Image

Udara @TGUPJ

9 months ago

🦎 un.ms/research

42 79 2K 136K 2K

Download Video

Tanishq Mathew Abraham, Ph.D. @iScienceLuvr

9 months ago

Reverse Thinking Makes LLMs Stronger Reasoners abs: arxiv.org/abs/2411.19865 "Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towards the problem. This often enhances overall reasoning performance as it…

17 152 751 58K 597

Download Image

Andrej Baranovskij @andrejusb

9 months ago

Sparrow Apple MLX Backend on Mac Mini M4 (Qwen2 72B 4bit) Running the Qwen2 72B 4bit model locally on a Mac Mini M4 for Sparrow’s backend. Thanks to MLX-VLM by @Prince_Canuma