rogerbai (@rogerbai6) 's Twitter Profile
rogerbai

@rogerbai6

Cloud architecture | AI Startup. Opinions my own.

ID: 1363034479325974531

calendar_today20-02-2021 07:55:25

194 Tweet

58 Followers

1,1K Following

Tom Yeh (@proftomyeh) 's Twitter Profile Photo

MLP by hand✍️Excel ~ I designed this exercise to show how to calculate a four-level network by hand, along with a graph and matching pytorch code. Also, I made a medium and a large version to show how it scales. 👇Join the 'AI Math' community. Download xlsx.

Franck Pachot (@franckpachot) 's Twitter Profile Photo

An appealing idea is the deep integration of DBMS and OS (minimizing the layers between DB and hardware). Oracle had many interesting concepts (Raw Iron, ASMLib, UEK, DAX for SPARC...) Separation of concerns often wins, but this one is cloud-native 🕺 cs.cit.tum.de/fileadmin/w00c…

大帅老猿 (@ezshine) 's Twitter Profile Photo

向所有自媒体创作者,独立开发者,一人企业,创业公司 强烈推荐!强烈推荐!强烈推荐!强烈推荐!强烈推荐! 影视飓风的 tim 在 3 年前分享的一期视频《一个百大UP主的创业故事》没看过的一定要看。 感谢 Orange AI 分享 bilibilibb.com/video/BV1Bb4y1…

Vaibhav (VB) Srivastav (@reach_vb) 's Twitter Profile Photo

Fuck it - it’s raining smol LMs - SmolLM2 1.7B - beats Qwen 2.5 1.5B & Llama 3.21B, Apache 2.0 licensed, trained on 11 Trillion tokens 🔥 > 135M, 360M, 1.7B parameter model > Trained on FineWeb-Edu, DCLM, The Stack, along w/ new mathematics and coding datasets > Specialises in

Fuck it - it’s raining smol LMs - SmolLM2 1.7B - beats Qwen 2.5 1.5B & Llama 3.21B, Apache 2.0 licensed, trained on 11 Trillion tokens 🔥

> 135M, 360M, 1.7B parameter model
> Trained on FineWeb-Edu, DCLM, The Stack, along w/ new mathematics and coding datasets
> Specialises in
Philipp Schmid (@_philschmid) 's Twitter Profile Photo

RAG Developer Attention! 🔔 Docling is a new library from IBM that efficiently parses PDF, DOCX, and PPTX and exports them to Markdown and JSON. It supports advanced PDF understanding and seamless integration with LlamaIndex 🦙 and LangChain. TL;DR: 🗂️ Parses numerous

RAG Developer Attention! 🔔 Docling is a new library from <a href="/IBM/">IBM</a> that efficiently parses PDF, DOCX, and PPTX and exports them to Markdown and JSON. It supports advanced PDF understanding and seamless integration with <a href="/llama_index/">LlamaIndex 🦙</a> and <a href="/LangChainAI/">LangChain</a>.

TL;DR:
🗂️ Parses numerous
Anderson Mancini (@andersonmancini) 's Twitter Profile Photo

Realistic Water Simulation with #threejs is live: water-simulation.vercel.app Now, you can configure scenes, objects, colors, and light positions. You can also dive to see the effects from underwater 🌊💧. It works great on mobile 🤩. The breakdown video will be on my YouTube

Hassan (@nutlope) 's Twitter Profile Photo

Introducing LogoCreator! An open source logo generator that creates professional logos in seconds using Flux Pro 1.1 on Together AI. 100% free and open source. Demo + code:

rogerbai (@rogerbai6) 's Twitter Profile Photo

Pretty good Tech Stack: CrewAI: The leading multi-agent platform Weaviate: The AI-native database for a new generation of software Groq: Fast AI Inference ExaSearchTool: The search engine for AI WebsiteSearchTool: Built in web rag tool from crewai_tools

Andy Pavlo (@andypavlo.bsky.social) (@andy_pavlo) 's Twitter Profile Photo

Buckle up because we're crashing into the new year with my annual database retrospective: License change blowbacks! Databricks vs. SnowflakeDB gangwar! @DuckDB shotgun weddings! Buying a college quarterback with database money for your new lover! cs.cmu.edu/~pavlo/blog/20…

Ammaar Reshi (@ammaar) 's Twitter Profile Photo

Just built a Perplexity clone using Gemini 2.0 + Grounding, and the wildest part? Replit ⠕'s Agent wrote ALL the code in 2 hours! Search anything, get sources, ask follow-ups. Google has all the pieces to make AI search incredible. Hope they productize it soon! Demo + code 👇

Yixin Ye (@bleavesye) 's Twitter Profile Photo

🤔 How many examples does an LLM need to learn competition-level math? Conventional wisdom: 100,000+ examples Our discovery: Just 817 carefully chosen ones 🤩 With pure SFT, LIMO achieves: 57.1% on AIME 94.8% on MATH LIMO: Less is More for Reasoning 📝 🔗 arxiv.org/pdf/2502.03387

🤔 How many examples does an LLM need to learn competition-level math?
Conventional wisdom: 100,000+ examples
Our discovery: Just 817 carefully chosen ones 🤩
With pure SFT, LIMO achieves:
57.1% on AIME
94.8% on MATH

LIMO: Less is More for Reasoning 📝
🔗 arxiv.org/pdf/2502.03387
Nomic AI (@nomic_ai) 's Twitter Profile Photo

Nomic Embed Text V2 is now available - First general purpose Mixture-of-Experts (MoE) embedding model - SOTA performance on the multilingual MIRACL benchmark for its size - Support for 100+ languages - Truly open source - open training data, weights, & code - Apache 2.0 License

Nomic Embed Text V2 is now available

- First general purpose Mixture-of-Experts (MoE) embedding model
- SOTA performance on the multilingual MIRACL benchmark for its size
- Support for 100+ languages
- Truly open source - open training data, weights, &amp; code
- Apache 2.0 License
Alexs🥇 (@real_alexs_) 's Twitter Profile Photo

This afternoon, I watched the recently popular movie #NeZha2. After watching it, I felt that rather than telling a Chinese mythological story, the movie is actually reflecting the current international reality. In the film, the Immortal Lord Wuliang talks about vanquishing

This afternoon, I watched the recently popular movie #NeZha2.

After watching it, I felt that rather than telling a Chinese mythological story, the movie is actually reflecting the current international reality. 

In the film, the Immortal Lord Wuliang talks about vanquishing
AA (@measure_plan) 's Twitter Profile Photo

I've open sourced this project! - use voice commands to change interaction mode (drag, rotate, scale, animate) - use hand gestures to control the 3D model - drag/drop to import other models (only GLTF format supported rn) created using Three.js, Rosebud AI, mediapipe computer