Hugging Face Developer Tooling
Hugging Face developer tooling, including Transformers, TRL, Jobs, MCP, CLI tools, agents, and Hub integrations.
24%
Best tweets about Hugging Face
50 Best Tweets About Hugging Face (2026)
Browse the best tweets about Hugging Face, from open models and datasets to Spaces, Transformers, inference, and machine learning workflows.
Technical Hugging Face releases, repositories, datasets, demos, libraries, and real model-building experience.
- Creators
- 43
- Updated
Original Xholic analysis
What 50 top Hugging Face posts reveal
The dataset emphasizes Hugging Face-linked open-model releases, developer tooling, customization and deployment, with generative-media posts showing the highest theme median score. It also contains cautionary posts about a reported security incident and an allegation about repository-use consent.
- Dominant tone
- Positive
- Median score
- 27.3
- Leading format
- Announcement
- Recent posts
- 40%
88% of posts
All-time engagement
72% of posts
Published in 90 days
Conversation map
The themes creators return to
Model Customization & Deployment
Post-training, fine-tuning, evaluation, quantization, local inference, and production serving of open models.
24%
Open Model Releases
Open-weight and open-source model releases on the Hugging Face Hub, including language, multimodal, reasoning, coding, and domain-specific foundation models.
24%
Generative Media
Generative media models and demos for image-to-3D, video, audio, music, speech, and visual creation.
18%
Datasets & Data Pipelines
Datasets published, hosted, streamed, or prepared through Hugging Face, especially scientific, robotics, synthetic, and web-scale data.
14%
Retrieval & Document AI
Retrieval, embeddings, OCR, document understanding, and RAG workflows built with Hugging Face models, datasets, and tooling.
14%
Spaces & Demos
Hugging Face Spaces, interactive demos, private-app deployment patterns, and featured community applications.
10%
Robotics & World Models
Robotics, embodied AI, world models, LeRobot, and real-world action-oriented model releases.
8%
Tone and stance
Sentiment Positive leads
Author posture Supportive leads
Performance benchmark
- Median likes
- 68
- Median reposts
- 15
- Median replies
- 8
- Median views
- 11.2K
Posts with media make up 72% of this collection. Their median all-time score is 82.7, compared with 2.85 for text-only posts.
Format mix
- Announcement 72% · score 50.1
- Case Study 10% · score 8.70
- List 6% · score 32.6
- Tutorial 6% · score 18.1
Consensus and debate
Where creators agree, and where they do not
Shared view
Hugging Face as a release surface
Open-model releases are a 24% theme in the dataset. Posts announce Kronos, Qwen3.5 small models, and Sarvam 30B/105B models, each with Hugging Face availability or links stated in the posts.
Shared view
Image-to-3D releases feature demos and checkpoints
Image-to-3D releases are repeatedly framed around textured assets and accessible testing or distribution. TRELLIS.2 posts mention a live Hugging Face demo and a Hugging Face checkpoint; the Hunyuan3D 2.1 post says its models are on Hugging Face.
Shared view
Post-training workflows are a recurring topic
The cited posts cover local training and export in Unsloth Studio, TRL v1.0 workflow changes, and an embedding fine-tuning pipeline that includes synthetic QA generation, hard-negative mining, export, and OpenAI-compatible serving.
Open debate
Security accounts differ in detail and certainty
The two cited posts describe the same security topic differently. One says OpenAI and Hugging Face were investigating a production compromise during a benchmark evaluation and sharing preliminary findings; the other reports an end-to-end breach and attributes its account to TechCrunch. The supplied posts do not independently establish the full scope of the incident.
Open debate
Automation appears alongside a repository-consent criticism
One post alleges that Hugging Face used repositories for model development or evaluation without permission, while another promotes ml-intern as an autonomous post-training agent that finds or creates datasets, trains models, evaluates results, and uploads to the Hub. Together, these posts place automation alongside a stated consent concern, without resolving that concern.
What performs
Patterns behind standout posts
Release and dataset posts comprise the listed outliers
The five listed benchmark outliers are the Kronos post (7,066.05), TRELLIS.2 post (4,074.73), Qwen3.5 small-model post (3,730.43), psychiatric-genetics dataset post (1,961.86), and another TRELLIS.2 post (1,892.63). These scores span 1,892.63–7,066.05, compared with the dataset median all-time score of 27.33.
Media-heavy generative content has the highest theme median
Media appears in 36 of 50 posts (72%). Generative Media has the highest listed theme median all-time score, 99.159. The cited posts include image-to-3D release material and a roundup of featured Hugging Face apps.
Tooling, deployment, and releases each have a 24% theme share
Developer Tooling, Model Customization & Deployment, and Open Model Releases are each assigned a 24% share in the theme analysis. The cited posts illustrate local training tooling, a security-related deployment topic, and a technical report with a Hugging Face link.
Statistical standouts
- View standout post 1 Score 7066.1 · 258.55× median
- View standout post 2 Score 4074.7 · 149.09× median
- View standout post 3 Score 3730.4 · 136.5× median
- View standout post 4 Score 1961.9 · 71.78× median
- View standout post 5 Score 1892.6 · 69.25× median
Creator landscape
Who shapes this conversation
The five most represented creators account for 20% of the selected posts.
-
1. Vaishnavi
@_vmlops
2 posts
-
2. Nav Toor
@heynavtoor
2 posts
-
3. DailyPapers
@HuggingPapers
2 posts
-
4. Ihtesham Ali
@ihteshamali
2 posts
-
5. Ilir Aliu
@IlirAliu_
2 posts
-
6. Maziyar PANAHI
@MaziyarPanahi
2 posts
Vaishnavi covers demos and Hub tooling
Vaishnavi's two cited posts cover TRELLIS.2's Hugging Face demo and an MCP-server update featuring the hf_fs tool and sandboxes for dataset analysis, model training, and Space creation.
Nav Toor spotlights model releases
Nav Toor's cited posts focus on Kronos, described as a financial-markets model with models on Hugging Face, and Hunyuan3D 2.1, described as an open-source image-to-3D release with models on Hugging Face.
Ilir Aliu links robotics releases and onboarding
Ilir Aliu's cited posts pair a description of the τ0-WM robot world-model release and its Hugging Face weights with a LeRobot onboarding post centered on `pip install lerobot`.
How this analysis was made
Themes, sentiment, stance, and post format are classified per tweet. All counts, shares, medians, creator concentration, freshness, and performance comparisons are then calculated directly from the published snapshot.
Xholic's all-time score compares engagement while accounting for reach, post age, and creator consistency. It is used for relative comparisons within this collection.
This report analyzes the exact 50-post snapshot shown below. AI identifies editorial categories and drafts explanations; all statistics are calculated from the snapshot, and every narrative claim is checked against cited posts before publication.
Best Hugging Face tweets
Top Hugging Face tweets from 43 creators
Ranked 01–50
- 01
@heynavtoor ·
🚨 Someone built an AI that reads candlestick charts the way GPT reads English. Trained on 12 billion records from 45 exchanges. Outperforms every model by 93%. Live BTC demo. Free. It's called Kronos. The first open source foundation model built for financial markets. Not a general AI repurposed for finance. An AI that speaks the native language of candlestick patterns. Every other model treats financial data like weather data. Kronos treats financial data like financial data. Here's what it does: → Price forecasting. Feed it candlesticks. It predicts where price goes next. → Volatility prediction. Forecasts how volatile an asset will be before it happens. → Zero-shot. No fine-tuning. Works on any asset, any market, any timeframe. → 45 exchanges. Binance, NYSE, NASDAQ, LSE, and 41 more. → 4 model sizes. 4M params runs on a laptop. 499M for max accuracy. → Live demo running right now. BTC/USDT. 24-hour forecast. Updated hourly. Here's the wildest part: → 93% more accurate than the leading time series model → 87% more accurate than the best non-pretrained baseline → All zero-shot. No fine-tuning. Out of the box. Hedge funds spend millions on proprietary models. Bloomberg Terminal costs $24,000/year. This runs on your laptop. Few lines of Python. Free. Built at Tsinghua University. Accepted at AAAI 2026. Models on Hugging Face. 11.6K GitHub stars. 2.4K forks. MIT License. 100% Open Source.
- 02
@_vmlops ·
MICROSOFT DROPPED A 4B PARAMETER MODEL THAT TURNS ONE IMAGE INTO A 3D ASSET IN 3 SECONDS and it's open source TRELLIS.2 fully textured, physically accurate 3D models with PBR textures out of the box not a rough mesh..not a placeholder roughness, metallic, opacity the kind of detail that makes things look real under any lighting and it handles the weird stuff too..open surfaces, hollow interiors, geometry that breaks every other tool the model doesn't know the word "limitation" apparently https://t.co/BoNwq30ulK demo is live on hugging face right now
Watch video
- 03
@Alibaba_Qwen ·
🚀 Introducing the Qwen 3.5 Small Model Series Qwen3.5-0.8B · Qwen3.5-2B · Qwen3.5-4B · Qwen3.5-9B ✨ More intelligence, less compute. These small models are built on the same Qwen3.5 foundation — native multimodal, improved architecture, scaled RL: • 0.8B / 2B → tiny, fast, great for edge device • 4B → a surprisingly strong multimodal base for lightweight agents • 9B → compact, but already closing the gap with much larger models And yes — we’re also releasing the Base models as well. We hope this better supports research, experimentation, and real-world industrial innovation. Hugging Face: https://t.co/wFMdX5pDjU ModelScope: https://t.co/9NGXcIdCWI
- 04
@MaziyarPanahi ·
🚨 Over 1 billion rows of psychiatric genetics data. Now on Hugging Face. ADHD. Depression. Schizophrenia. Bipolar. PTSD. OCD. Autism. Anxiety. Tourette. Eating disorders. 12 disorder groups. 52 publications. Every GWAS summary statistic from the Psychiatric Genomics Consortium. Before: wget, gunzip, 20 minutes debugging separators, repeat 50 times. Now: one line of Python.
- 05
@ihteshamali ·
🚨BREAKING: Microsoft open sourced a 4B parameter model that generates production-ready 3D assets from a single image, and the speed numbers are genuinely hard to believe. It's called TRELLIS.2 and it uses a new geometry format called O-Voxel that can be converted to a textured mesh in under 100 milliseconds on CUDA, which means real-time 3D asset generation is now actually within reach. Most image-to-3D tools force you to pick between speed, quality, and topology correctness. TRELLIS.2 refuses that tradeoff by representing geometry natively in a sparse voxel format that supports arbitrary complexity from the start. → Outputs GLB files with full PBR texture maps ready for Blender, Unity, and Unreal Engine → Pretrained TRELLIS.2-4B checkpoint available directly on Hugging Face with model card and usage details → Web demo live now so you can test it without installing anything 4.6K stars. MIT License. 100% Opensource. Link in comments.
Watch video
- 06
@UnslothAI ·
Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: https://t.co/2kXqhhvLsb Blog and Guide: https://t.co/ENuTWal5AA Available now on Hugging Face, NVIDIA, Docker and Colab.
Watch video
- 07
- 08
@pratykumar ·
📢 Open-sourcing the Sarvam 30B and 105B models! Trained from scratch with all data, model research and inference optimisation done in-house, these models punch above their weight in most global benchmarks plus excel in Indian languages. Get the weights at Hugging Face and AIKosh. Thanks to the good folks at SGLang for day 0 support, vLLM support coming soon. Links, benchmark scores, examples, and more in our blog - https://t.co/DcCG3zlN8p
- 09
@heynavtoor ·
🚨 Professional 3D artists are going to hate this. Tencent open sourced an AI that turns a single photo into a production-ready 3D model with full PBR textures. The kind that ships in AAA games. The kind that renders in Unreal Engine without post-processing. The kind that takes a senior 3D artist 3 to 5 days to build by hand. It's called Hunyuan3D 2.1. The first fully open source production-ready 3D generation model. Full weights. Full training code. Free. Upload one photo of anything. Get a complete 3D model with Albedo, Normal, Roughness, and Metallic maps. Ready for Blender. Ready for Unity. Ready for Unreal Engine. No 3D modeling skills required. Not a toy. Not a research demo. Production-ready assets that work in real game engines and film pipelines. No Maya license. No Substance Painter subscription. No $125/hour artist retainer. Here's what it does: → Image to 3D. Upload one photo, get a full 3D mesh in seconds. → Text to 3D. Describe any object in words, get a 3D model. → PBR texture synthesis. Metallic reflections, subsurface scattering, physically accurate materials. → Outperforms every open source AND closed source 3D generation model in benchmarks. → Full model weights released. Fine-tune it for your own use case. → Full training code released. First time ever for a model at this level. → Runs on 10GB VRAM for shape generation. → Supports macOS, Windows, and Linux. → Blender addon included. ComfyUI integration available. Here's the wildest part: This solves the "Janus problem." Where AI-generated 3D models have a different face on every side. Hunyuan3D 2.1 generates a clean mesh first, then projects PBR textures from multiple angles simultaneously. Coherent geometry. Seamless textures. Every angle looks correct. 3D artists charge $500 to $5,000 per model. Game studios pay $50,000 to $200,000 per year for 3D asset pipelines. Film VFX houses spend millions on modeling teams. Indie developers can't afford professional 3D assets at all. This generates them from a photo. On your GPU. For free. 3.1K GitHub stars. 447 forks. Built by Tencent. Published on arXiv. Models on Hugging Face. 100% Open Source. Apache 2.0 License.
- 10
@rpnickson ·
LTX-2 is the first truly open-source audio-video generation model, and it's extremely impressive. Production-grade, native 4K 50 FPS output generated entirely on your own hardware. 2,382,172 Hugging Face downloads in the last month says it all. @ltx_model 👏
Watch video
- 11
@ihteshamali ·
If you want to become an AI engineer in 2026 and don't know where to start. Here's the complete list of free resources you actually need. 1. Stanford CS229- Machine Learning The course Andrew Ng built before he became Andrew Ng. Full lectures on YouTube. Problem sets on the Stanford site. Audit free on Coursera. Link: https://t.co/K2kFE3dHQ8 2. Harvard CS50 AI - Intro to AI with Python The cleanest beginner AI course on the internet. Harvard puts it out for free. No excuses. Link: https://t.co/LMf6IJeOZp 3. MIT 6.S191 - Deep Learning MIT's official intro to deep learning. Updated every year. Guest speakers from Google, Microsoft, MIT labs. Link: https://t.co/N7WsOA7UDZ 4. UC Berkeley - LLM Agents MOOC Guest lectures from Anthropic, OpenAI, Google DeepMind, and NVIDIA on how agents actually work. The most industry-relevant free course on agents right now. Link: https://t.co/hLGAcVNd5u 5. Hugging Face LLM Course Covers transformers, fine-tuning, deployment, and advanced LLM techniques. Built by the team that ships the tools you'll actually use on the job. Link: https://t.co/apLq1Y652G 6. Hugging Face AI Agents Course Goes from theory to production. You build with smol-agents, LangGraph, and LlamaIndex. Free certificate included. Link: https://t.co/8QYPr5l6gM 7. Anthropic Academy – Developer Deep Dive 13 free courses from the team that built Claude. Covers the API, MCP, prompt engineering, and production integration patterns. Launched March 2026. No paywall. Link: https://t.co/JLRiDIzbPe 8. Anthropic Prompt Engineering Course 9 chapters, hands-on exercises, runs directly in Claude. The only prompt engineering course where you learn from the people who built the model. Link: https://t.co/ZIiTGzEdo8 9. DeepLearningAI Short Courses 88 free courses. Each one runs 1–2 hours. Built with OpenAI, LangChain, Anthropic, and Mistral. Start with "ChatGPT Prompt Engineering for Developers." Link: https://t.co/btuHWx2zEo 10. fast AI - Practical Deep Learning for Coders Jeremy Howard's course. Code-first. No math gatekeeping. The fastest way to go from zero to actually building neural networks. Link: https://t.co/yWbkhFTbuu All of it is free. None of it requires a paid subscription. If you could only pick ONE of these to start with in 2026, which would it be?
- 12
@natjin ·
> train embeddings model on actual web search > use it in actual production (200M daily queries) > see crazy results: best contextual retrieval in the world (81.96% CoNTEB; next closest 79.45%) > open source it > 1M hugging face downloads in ~2 weeks > 5-30x cheaper than existing providers > go try it :) (pplx-embed on @huggingface)
- 13
@arcee_ai ·
Today we're releasing Trinity-Large-Thinking. Available now on the Arcee API, with open weights on Hugging Face under Apache 2.0. We built it for developers and enterprises that want models they can inspect, post-train, host, distill, and own.
Watch video
- 14
@minchoi ·
Hugging Face just made arXiv paper retrieval way better for AI agents. 𝚑𝚏 𝚙𝚊𝚙𝚎𝚛𝚜 [𝚜𝚎𝚊𝚛𝚌𝚑, 𝚛𝚎𝚊𝚍] turns arXiv into agent-ready markdown👇
Watch video
- 15
@KanikaBK ·
😱 I SPENT 3 HOURS TESTING THIS SO HERE IS WHAT ACTUALLY MATTERS. Kronos is a foundation model built from scratch on the language of financial markets. 45 global exchanges. AAAI 2026 accepted. MIT license. Every trading model being built from scratch right now is already behind. The crazy part? Most people building trading models right now have NO IDEA this already exists. While everyone else is still coding from scratch. Here is what makes it different from every other trading model: ↳ Trained specifically on financial candlestick data not repurposed from general time series models ↳ Handles OHLCV data natively. Open, high, low, close, volume and amount all in one model ↳ Novel two-stage framework. Specialized tokenizer converts continuous market data into discrete tokens first. Then a large autoregressive transformer learns from those tokens ↳ Designed to handle the unique high-noise characteristics of financial data that break general purpose models ↳ Trained across 45 global exchanges for broad market understanding Four models available today: ↳ Kronos-mini — 4.1M parameters. Lightweight. Fast. Deploy anywhere. ↳ Kronos-small — 24.7M parameters. Strong performance for most use cases. ↳ Kronos-base — 102.3M parameters. Full power. Production ready. ↳ Kronos-large — 499.2M parameters. Research grade. Coming soon. All on Hugging Face. All free. Raw data to forecast in four lines of code: ↳ Load the tokenizer and model from Hugging Face ↳ Pass your historical OHLCV data ↳ Define your prediction length ↳ Call predict No feature engineering. No manual preprocessing. Just raw candles in and forecasts out.
- 16
@Meituan_LongCat ·
🚀 LongCat-Flash-Thinking-2601 Technical Report – Now Fully Released! Key insights: 🌍 Large-scale agentic RL (14 pages of deep dives!) 🔹 Environment scaling: A detailed look at our automated pipeline that builds 10,000+ executable, verifiable environments across 20+ domains. 🔹 RL infrastructure: An upgraded DORA framework that supports async training with 32,000+ concurrent environments, tackling stability issues in long-tail and highly heterogeneous tasks. 🛡️ Robustness in the wild 🔹 Noise injection: No more "greenhouse" agents. We systematically analyze real-world noise (user/tool noise) and inject it directly into the training loop. 🔹 Curriculum RL: A curriculum-based strategy that gradually toughens the model against messy, imperfect environments. 🧠 Heavy Thinking framework 🔹 Parallel reasoning: Expands breadth by generating multiple independent reasoning trajectories. 🔹 Iterative summarization: Expands depth by using a summary model to reflect on and synthesize parallel trajectories before making final decisions. 🔹 Context memory: A purpose-built memory module to keep reasoning coherent over long horizons. ⚡ Zigzag Attention 🔹 Zigzag Connectivity design combining MLA + SSA to reduce compute while preserving global information flow. 🔹 Mid-training switch to sparse variants yields a 1.5× speedup and supports 1M-token contexts —laying the groundwork for future breakthroughs in long-context agentic reasoning. 🔹 Explore：https://t.co/xmvQ2kmJUV 📊 Achieves SOTA among open-source models across key agentic benchmarks: search, tool use, mathematical reasoning, and coding. If you want more details, feel free to check out the full technical report. • Paper: https://t.co/X7h2092UN5 • Website: https://t.co/d6cZdCPWnh • GitHub: https://t.co/24sd7zY98j • Hugging Face: https://t.co/UCmFfzqTlj
- 17
@AbdelStark ·
Why LLMs are a dead end for human-level intelligence, and especially for Physical AI / Robotics. The next leap isn’t bigger language models. It’s World Models. I just dropped a full 1-hour presentation from Shanghai: “World Models: the ChatGPT moment for robotics?” → Why LLMs hit a wall → Why action-conditioned world models planning in latent space are the real path → Live World Forge demo with LeWorldModel + Hugging Face LeRobot Watch here. The future of intelligence is embodied, not just chatty.
Watch video
- 18
@heygurisingh ·
🚨RAG engineers are going to lose their minds. @webAI just open sourced a document retrieval model that's sitting at #1 AND #3 on ViDoRe V3 -- with Nvidia's best open-source embedding model trapped at #2 between them. No OCR. No text extraction. No broken pipelines on messy PDFs. It's called webAI-ColVec1. Here's what this thing actually does: → Skips OCR entirely and retrieves directly from the rendered page image -- sees layout, tables, charts, and structure the same way you do → Ships in two variants (4B and 9B) with embedding sizes of 128, 640, and 2560 -- pick speed or max retrieval quality → Trained on ~2M question-image pairs across scientific papers, financial filings, healthcare records, government reports, and technical manuals → Uses 511 in-batch negatives per query for a brutal contrastive signal that forces clean separation between correct and competing pages → Built with a proprietary loss function designed specifically for retrieval -- not borrowed from generic embedding training → LoRA rank 32 + retrieval projection layer means efficient specialization without full fine-tuning Here's the wildest part: Built on Qwen 3.5 vision-language backbones and trained on just 8 A100s. No giant model. No massive infra budget. No scale-maxing. Just a deliberate, retrieval-specific training recipe applied to the right problem. And it beat the largest GPU company in the world on their own benchmark. You literally point this at a financial filing or a scanned healthcare doc -- the stuff that destroys every OCR pipeline in production -- and it retrieves the right page based on what the page actually looks like. That sentence shouldn't be real for an open-source model trained on 8 GPUs in 2026. But here we are. 100% Open Source. Live on Hugging Face. Two of the top three spots on ViDoRe V3. (Link in the comments)
- 19
- 20
@IlirAliu_ ·
The first open-source unified world model for scalable robot manipulation: 5B-parameter open-source unified video-action world model that combines policy and world modeling to generate robot actions, predict future visuals, and evaluate task progress from observations, language, and state. The model is trained on 27.3K hours of heterogeneous data (17.8K real-robot teleop, 6.5K UMI demos, 3K egocentric human videos), enabling it to perform complex manipulation tasks like faucet connecting, bag packing, and toolbox storing as shown in demo videos. The approach supports test-time action refinement and points toward deployment-driven continuous improvement via fleet data. Thanks for sharing, Jianlan Luo (@jianlanluo)! 📌 Resource links for τ0-WM: • Project page: https://t.co/YaA5XRBtZF • GitHub (code): https://t.co/pYlH5xUFoC • Hugging Face (model weights): https://t.co/q5QQVHfYf1 • Paper (PDF): https://t.co/qpcfLvrkeP ——- Weekly robotics and AI insights. Subscribe free: https://t.co/9Nm01QUKlB
Watch video
- 21
@techNmak ·
Hugging Face put out a repo that lets you build a full voice assistant, the kind that listens, thinks, and talks back, entirely with open-source models. It's a pipeline with four stages: - voice activity detection, - speech-to-text, - an LLM, and - text-to-speech Each running in its own thread. Every single stage is swappable, you can pick different STT models, different TTS models, different LLM backends, all through CLI flags. And the whole thing is exposed through a WebSocket API that's compatible with OpenAI's Realtime API, so anything built for that protocol can talk to it without changes. This pipeline is already running in production, it's the conversation backend for thousands of Reachy Mini robots. Install is one line "pip install speech-to-speech", and by default it spins up a local server using Parakeet TDT for transcription and Qwen3-TTS for speech output, with the LLM slot pointed at whatever OpenAI-compatible endpoint you give it.
- 22
@IlirAliu_ ·
ETH has semester-long courses. Stanford? Lecture halls. MIT 826-page textbooks. 📌 Hugging Face’s robotics? 10 minutes… >pip install lerobot That’s it. This command gets you started: Classical foundations. Imitation learning. Reinforcement learning. Foundation models. Real datasets. Real robots. The gap between academic and accessible is closing faster than most people realize. And that matters more than any single course. 📌[https://t.co/QVOjxYFPhd] ——- Weekly robotics and AI insights. Subscribe free: https://t.co/9Nm01QUcw3
- 23
- 24
@DAIEvolutionHub ·
40 Truly Useful GitHub Repositories Every Developer Should Know Not because they're trendy. Because they actually help you learn faster, build better, and save hours every week. Learn Computer Science & Engineering • Build Your Own X → Build databases, Git, Docker, and more from scratch https://t.co/BKnK2mXNu9 • Developer Roadmap → Step-by-step roadmaps for every major tech stack https://t.co/jME7PVbBfX • Coding Interview University → Complete CS curriculum for software engineers https://t.co/inAR6tL0Bk • System Design Primer → The most recommended system design resource https://t.co/fPYxzvxYCn • Tech Interview Handbook → Interview prep, algorithms, and behavioral guides https://t.co/TATOXQoPS4 • Project-Based Learning → Learn by building real projects https://t.co/1C3tWvBDss • Free Programming Books → Thousands of free programming books and courses https://t.co/lnK5LHMx9d • freeCodeCamp → Learn to code completely free https://t.co/HGX6udgqz5 Become More Productive • Public APIs → Massive collection of free APIs https://t.co/1u5LAowSWo • Gitignore → Ready-made .gitignore templates for every language https://t.co/ccpMK13pIk • The Art of Command Line → Become faster in the terminal https://t.co/4gKtXk2j53 • 30 Seconds of Code → Copy-paste JavaScript snippets https://t.co/SfdO0m5iIh • JavaScript Algorithms → Algorithms explained with visuals https://t.co/KG4n64dJQB • You Don't Know JS → One of the best JavaScript deep dives https://t.co/2566ljZjs0 • The Book of Secret Knowledge → Huge collection of developer resources https://t.co/dxaxnrf0XO AI & Agent Stack • Ollama → Run LLMs locally https://t.co/pSPuwpBB6X • LangChain → Build LLM-powered applications https://t.co/ns4aMElunl • Dify → Visual AI app builder https://t.co/5n515pe0vY • Langflow → Drag-and-drop AI workflows https://t.co/J0vuq4iDsj • CrewAI → Multi-agent collaboration framework https://t.co/L5Ek3G6XUn • AutoGen → Microsoft's agent framework https://t.co/MogAZ0Z9BK • MetaGPT → AI software company simulation https://t.co/YmAwhhxFvT • Mem0 → Long-term memory for AI agents https://t.co/iRVzhBjwsX • Browser Use → Let AI control browsers https://t.co/vNcm1mA4EE • Open WebUI → Self-host your ChatGPT alternative https://t.co/WfCqfddjS1 • Aider → AI pair programmer inside your terminal https://t.co/5RsnQutytk • n8n → AI-powered workflow automation https://t.co/pmMLX1OLtH • OpenClaw → Open-source desktop AI assistant https://t.co/qY0F8w8XyI • Ruflo → Claude agent orchestration https://t.co/rYYcM74jcw • Hermes Agent → Autonomous AI agent framework https://t.co/hves4Mqgj0 • Agency → Launch AI agencies with reusable agents https://t.co/Ktf7a3Ijw9 • TradingAgents → Multi-agent trading research https://t.co/xunNFf8ZxT • Browserbase Skills → Web automation skills for AI agents https://t.co/p3zCjiy4Pm • Lobe Chat → Beautiful AI workspace https://t.co/QZUVri1gtC • Hugging Face Transformers → Industry-standard ML library https://t.co/AtyDLv7NXI • CocoIndex → Long-context retrieval engine https://t.co/ENefJTh0AJ • MarkItDown → Convert documents into Markdown https://t.co/wfxHGaPVSe Security & Self-Hosting • Awesome Selfhosted → Thousands of self-hostable apps https://t.co/caLDANTEHu • Maigret → Username search across 3,000+ websites https://t.co/BLB1pt1uyM • Stable Diffusion WebUI → Generate AI images locally https://t.co/py6hCAIY7Q Save this somewhere. Six months from now, you'll probably end up using at least half of these.
- 25
@sharbel ·
Google Research built a pretrained foundation model for time-series forecasting. It's called TimesFM. You pip install it. You load your data. You call forecast. You get predictions back in seconds. No account. No API key. No data leaving your machine. Here's what it does: → Zero-shot forecasting on any time series. No training required. Point it at new data and it predicts. → 200M parameter transformer model. Decoder-only architecture. The same paradigm that powers LLMs, applied to numbers. → Up to 16,000 context length. Feed it years of history and it uses all of it. → Continuous quantile forecasting up to 1,000 horizon steps via an optional 30M quantile head. → Covariate support via XReg. Add external variables that influence your forecast. → Fine-tune on your own data with LoRA via HuggingFace Transformers and PEFT. → PyTorch and Flax backends. Runs on CPU, GPU, TPU, and Apple Silicon. → Checkpoints on Hugging Face. One line to download the latest model. → Integrates with BigQuery ML for enterprise SQL-based forecasting at scale. → Works inside Google Sheets for spreadsheet-level forecasting. → Agentic calling support via Vertex Model Garden and SKILL.md. → pip install timesfm. That's the entire setup. Apache-2.0 licensed. Self-hosted. Open weights on Hugging Face. Free forever. 100% Open Source. Github repo link: https://t.co/kTn6IRtMcM
- 26
@ai_for_success ·
⚡ Google DeepMind just dropped DiffusionGemma, latest experimental open model (Apache 2.0) that generates text up to 4x faster. - Uses diffusion instead of traditional next token autoregressive generation - Generates and refines 256 token blocks in parallel - Achieves up to 700+ tokens/sec on RTX 5090 and 1000+ tokens/sec on a single H100 - Designed as a 26B MoE model but activates only 3.8B params during inference - Can run quantized within 18 GB VRAM - Supports bidirectional attention during generation - Can self correct outputs during inference through iterative denoising - Handles global context much better than standard left to right models - Particularly strong for constraint based tasks like Sudoku - Fine tuned Sudoku version reached 80% success while base model was near 0% - Uses block autoregressive diffusion for long context generation - Integrated directly into vLLM for OpenAI compatible serving - Released with official training recipes and fine tuning support - Optimized across RTX 4090, RTX 5090, Hopper, and Blackwell GPUs Getting started: - Model weights are available publicly on Hugging Face - Works with vLLM, Hugging Face Transformers, and MLX - Deployable through Google Cloud Model Garden and NVIDIA NIM - Google released official fine tuning recipes through Hackable Diffusion License: - Released under Apache 2.0 - Allows commercial usage - Allows modification and redistribution - Developers can fine tune and build products on top of it This is one of the strongest public signs yet that major labs are actively exploring post autoregressive architectures for future LLMs.
Watch video
- 27
@socialwithaayan ·
HUGGING FACE JUST OPEN-SOURCED THE ML INTERN EVERY RESEARCHER HAS DREAMED OF No more spending days reading papers and writing training scripts. ml-intern is an autonomous agent that reads ML papers, discovers datasets, trains models, debugs failures, keeps iterating, and ships production-ready models to the Hub all by itself. It automates the entire end-to-end post-training workflow using the full Hugging Face ecosystem. This is the agent that turns "I have an idea" into a working model while you sleep. What it actually does: → Reads arXiv papers and understands the latest research → Finds or creates the right datasets → Writes clean training code and runs it on real compute → Evaluates results and iterates automatically → Packages and uploads everything to HF Hub with proper structure Built on smolagents with proper tool access, context compaction, and safety checks. One prompt. Real results. No hand-holding. 5.8k stars in days and still exploding. The future of machine learning research just became open source. 100% Open Source.
- 28
- 29
@victormustar ·
Featured Apps you can try on Hugging Face this week 🔥 🗣️ Voxtral TTS Demo: Mistral's new text-to-speech 🎙️ Cohere Multilingual ASR: multilingual transcription ⚡ Cohere WebGPU: same but locally in your browser 🎩 Mr. Chatterbox: Victorian-era gentleman chatbot 🎵 PrismAudio: text-prompted audio for video 🌍 PROMETHEUS v1.0: embodied AI world model 🎨 VFig Image2SVG: diagrams to editable SVGs 🕺 LTX 2.3 Sync: portrait animation & lipsync
- 30
@fortytwonetwork ·
20,000+ downloads reached on Hugging Face for the Fortytwo Rust Coder Model ✷ The model was trained on data generated by Fortytwo node operators ✷ Five quantized versions shipped by independent devs ✷ 43.00% (SOTA) on the RustEvo^2 benchmark One more example of the AI community outpacing centralized labs Get it on Hugging Face ↓
- 31
@MaziyarPanahi ·
You can make a Hugging Face Space private but keep its URL publicly accessible. Private repo. Public app. No one sees your code, everyone uses your endpoint. I deploy private medical endpoints for clinical agents this way. HIPAA-sensitive inference behind a public API. Didn't know this existed until last week. What's your favorite hidden @huggingface feature?
- 32
@lancedb ·
@dlthub and @huggingface 🤗 just shipped a clean way to ingest Hugging Face datasets into LanceDB 🚀 Query datasets over hf:// with DuckDB, stream them in batches, and load them into LanceDB with embeddings generated during ingest. The result is a simple Python path from Hub dataset to a searchable, explorable table.
- 33
@DivyanshT91162 ·
Yann LeCun just reposted it. Why is everyone suddenly talking about Unlimited-OCR? Baidu's Unlimited-OCR is back in the Top 3 trending AI projects on Hugging Face, once again ranking ahead of GLM-5.2. Last month it dominated GitHub and Hugging Face trend charts. Most people thought the hype was over. Then a Turing Award winner shared it... and it shot right back to the top. Now it has: • 16.5K+ GitHub stars • 2.24M+ Hugging Face downloads • Still growing fast. The biggest problem with traditional OCR is that it processes documents page by page. That breaks multi-page tables, loses reading order, and struggles with long PDFs. Unlimited-OCR takes a different approach. Using its R-SWA architecture, it processes dozens of pages as a single continuous document while keeping KV Cache memory constant—so GPU memory doesn't keep increasing as documents get longer. Independent tests showed it could parse a 100-page PDF in one run while maintaining an error rate below 0.11 even after page 40, where many OCR systems begin to fail. Despite all that, it's only a 3B model, runs locally on consumer hardware, and is completely free. If you regularly work with research papers, contracts, books, or scanned PDFs, this could replace expensive OCR tools and eliminate manual page splitting. Repo👇
- 34
@socialwithaayan ·
I found an AI tool yesterday that made me put my headphones back on three times. It's called JazzCat. An anonymous AI music model showed up on Hugging Face with no explanation. No company page, no launch post, no one claiming credit for it. Two features: 🔵 Text-to-Song ↳ You describe the vibe, genre, mood, and instruments ↳ JazzCat generates an entire original song from scratch ↳ Lyrics, vocals, and full production come back from a single text prompt 🔵 AI Cover ↳ You give it a reference track ↳ It generates an AI vocal cover ↳ I played one for a friend and he genuinely thought it was a real artist Two features and both of them are unreasonably good. There's no $50/month subscription. No enterprise tier. No sales team in your DMs. It's a Hugging Face demo that outperforms tools backed by actual venture funding. I keep finding that the most impressive AI work in 2026 comes from people who never announce anything. They just ship and let the output speak for itself
- 35
- 36
- 37
- 38
@mark_k ·
MiniMax H3 is now open on Hugging Face! 🔥 @Hailuo_AI released the weights for H3, their general-purpose omni-modal generative model. It unifies text, images, video, and audio in one context and generates video with native stereo audio, up to 15 seconds at 2K. Key points: - Strong instruction following, accurate text and brand rendering, and video-to-video motion transfer - Aimed at advertising, branding, e-commerce, product design, and gaming - Competitive pricing, with 2K costing less than a third of mainstream models - 33B-parameter Omni-Transformer conditioned on Qwen3-VL-32B Two main checkpoints available: FL2VA and Ref2VA. Local inference works with Diffusers, SGLang, vLLM, and native ComfyUI support. One of the strongest open video models released so far.
- 39
@DataChaz ·
AN @HUGGINGFACE ENGINEER JUST CRUNCHED 1.2M COMMONCRAWL PAGES FOR UNDER $1 🤯 Zero Slurm cluster required. How? DataTrove now runs natively on Hugging Face Jobs. → Same pipeline code, just a simple executor swap → Cloud tasks fan out automatically → CPU filtering + GPU inference all in one chain 🔥 Mind-blowing efficiency. Details in 🧵 ↓
- 40
- 41
@smratitiwa86867 ·
Local LLMs just hit a whole new level 🤯 This Hugging Face release is actually insane: "gpt-oss-20b-tq3" An official 20B+ parameter MoE model from OpenAI… quantized to 3-bit with TurboQuant + optimized with MLX… …and now it runs smoothly on a normal 16GB MacBook. 💻 No server. No cloud bill. No internet needed. Everything stays fully local. A few months ago this would’ve needed a high-end GPU setup. Now an M-series Mac can handle it. • 131K context window • Fully offline + private • Great for chat, writing, and coding • 60–80 tok/s decoding speed • No monthly subscription Running top-tier open-source LLMs directly on a laptop doesn’t even feel real anymore
- 42
@ATechAjay ·
Need to build an AI that understands images? SenseNova-Vision is an open-source vision foundation model that unifies many computer vision tasks behind a single natural-language interface. You usually end up with something like this: → One model for object detection. → One model for segmentation. → One model for OCR. → One model for depth estimation. → One model for 3D reconstruction. Building computer vision apps has always felt like assembling LEGO pieces from five different boxes. Different APIs. Different output formats. Different pipelines. Maintaining everything becomes harder than building the product itself. Instead of stitching together multiple specialist models, SenseNova-Vision lets you describe the task in natural language. ✅ Detect every person ✅ Segment the road ✅ Read the text ✅ Estimate depth ✅ Reconstruct this object in 3D Same model. Same interface. Same set of weights. The interesting part isn't that it supports many vision tasks. It's that vision starts behaving like a foundation model. Instead of treating detection, segmentation, OCR, and 3D as separate AI systems, they're all expressed through natural language prompts. That means less time wiring models together... …and more time building products. Even better, the entire project is open source: ⭐ Model ⭐ Code ⭐ 50M-example training dataset ⭐ Benchmarks ⭐ Technical report ⭐ Interactive demo If you're building AI products, this is worth checking out. And if you appreciate open-source work like this, consider dropping the repo a ⭐️ GitHub: https://t.co/9T5tOvzis8 🤗 Hugging Face: https://t.co/dfCHgYbmD8
- 43
- 44
- 45
- 46
@JeremyCMorgan ·
Hugging Face and NVIDIA published an end-to-end embedding fine-tuning pipeline for RAG. Synthetic QA generation, hard negative mining, ONNX/TensorRT export, deployed behind an OpenAI-compatible API. Recall@60 went from 0.751 to 0.951 in one case. Requires 80GB VRAM for fine-tuning. https://t.co/MVNi4175JB
- 47
@boyuan_chen ·
The most important AI release yesterday wasn't Gemma 4. Hugging Face shipped TRL v1.0. Their post-training library has been the open-source default for SFT, DPO, GRPO, and reward modeling for years. 3 million monthly downloads. 130,000+ public models trained on earlier versions. Unsloth, Axolotl, LlamaFactory all build on it. Until this week, it was a research codebase with research-grade stability. Things broke between releases. Production teams kept internal forks to dodge upstream surprises. v1.0 adds a unified CLI, config-driven workflows, and stable APIs with deprecation guarantees. A team that needed distributed RL expertise to run custom GRPO can now do it from a config file. Post-training compute runs roughly 30x pre-training in serious pipelines now. The phase everyone treated as fine-tuning cleanup consumes the majority of GPU spend. The open-source tooling for it was held together with custom scripts until yesterday. Same day TRL shipped, Google dropped Gemma 4 under full Apache 2.0 and Alibaba launched Qwen 3.6-Plus. Both strong enough that teams will actually download and adapt them. Gemma's 26B MoE runs quantized on a MacBook Air. Qwen 3.6-Plus ships with native Anthropic API compatibility for agent stacks. Every team that grabs one of these needs SFT and preference optimization to make it useful for their workload. Production-grade post-training tooling and two base models worth running it on, all landing in the same 24-hour window. Anyone doing alignment work with custom scripts and internal patches just ran out of excuses.
- 48
@free_ai_guides ·
Hugging Face's database engineer just explained how they serve 3 million AI models without the platform melting. You might know the name from last week's news. This is the company OpenAI's rogue agent hacked to steal benchmark answers. Here's what they do the other 364 days: host the world's largest open AI model library, 14 million users, 30% of the Fortune 500. This 21-minute talk is the machine underneath: 00:00 - Scaling the Hub from 20K to 3 million models 03:57 - The point where regex search dies 07:55 - Inside a single "llama" search 13:00 - The 7-node cluster with a hidden analytics node 16:42 - Sharding for the next 10x 18:14 - Autoscaling from 10 to 500 pods Every chapter has numbers you can steal for your own stack. Watch it, then read the guide on investing in AI below.
Watch video
- 49
@_vmlops ·
Hugging Face just made its MCP server a lot smarter ▪️ new hf_fs tool unifies repos, storage, docs, and papers into one searchable interface ▪️ full Hub navigation now costs just over 1,000 tokens ▪️ sandboxes add secure execution for dataset analysis, model training, and Space creation https://t.co/7COmapUBGO
- 50
Best Tweets by Topic