Computer Vision • Multimodal AI • @huggingface Fellow ML🤗 • Computational Intelligence • Diffusion-Driven Adapters • https://xitter.cf/t.co/CZfzd6KVRA
India
Joined October 2022
- Tweets7.8K
- Following800
- Followers589
- Likes15.5K
Pinned Tweet
Qwen3-VL-Video-Grounding Demo. Perform point tracking, text-guided detection, and video question answering, all powered by the Qwen3-VL-4B vision-language model with real-time bounding box detection and cross-frame object matching. 🤗 @huggingface Demo in 🧵
Prithiv Sakthi retweeted
Papers with Code is now open-source!
Apache 2.0-license.
Let's collaboratively make the best paper interface!
github.com/huggingface/paper…
Prithiv Sakthi retweeted
🚀Excited to announce Nanbeige4.3-33B!
To push the performance ceiling of small agents, our strategy in Nanbeige4.3 starts with building a powerful teacher first.
Nanbeige4.3-33B delivers SOTA agentic performance among open models at ~30B parameters:
* Strong results on agentic coding and cowork benchmarks.
* When integrated into mainstream agent harnesses, it tackles real-world tasks with cost-efficient inference.
* It will serve as a teacher for upcoming smaller Nanbeige models, starting with Nanbeige4.3-3B.
huggingface.co/Nanbeige/Nanb…
huggingface.co/Nanbeige/Nanb…
#LLM #Agent
Prithiv Sakthi retweeted
We benchmarked 17 open OCR models on OmniParseBench, our new OCR benchmark that builds on AllenAI's olmOCR-bench.
Prithiv Sakthi retweeted
Tencent just released WeVisOne-VL on Hugging Face
A unified vision-language model that handles detection, referring, counting, pointing, OCR, segmentation, and matting in one model.
Prithiv Sakthi retweeted
Introducing Carbon-X: The best open DNA model.
We midtrained a 14B model on DNA and text, and it beats every open language model and matches GPT-6.1 Sol at 1,000x lower cost.
Ask it about a sequence, what a mutation does, or to generate new DNA.
huggingface.co/HuggingFaceBi…
Prithiv Sakthi retweeted
Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine.
• Best-in-class fast local coding
• Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark
• Built from scratch in under 4 months
Private, unmetered intelligence on your own machine. Open weights available now on @huggingface, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.
Prithiv Sakthi retweeted
BOOM! I trained my own judge on the Jev datasets. It beat Jev 1.14 🔥
Open 4B, 22 min on one NVIDIA H200 on Hugging Face Jobs, $1.87
4,035 held-out RAG + safety calls:
Jev 1.14: 82.2%
my 4B: 89.4%
Twist: on PubMed answers it never saw, Jev wins. Unless it learns from Jev 👀
Prithiv Sakthi retweeted
A new frontier for on-device speech.
We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date.
Phonon-31m is available under Apache 2.0.
gradium.ai/phonon🧵
Prithiv Sakthi retweeted
The Muse Glimmer technical report is out: arxiv.org/pdf/2610.24628v1Mu…
Muse Glimmer is our 30B open-weight model (Apache 2.0), designed for agentic workloads entirely on consumer hardware.
Looking forward to seeing how the community uses our model!
Prithiv Sakthi retweeted
Aloha!🌺 Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast
Stronger. Faster. Leaner. Ornith-1.5-122B delivers frontier-level capabilities with exceptional inference efficiency. With superior instruction following, stronger task decomposition, and deeper understanding of real-world workflows, it achieves state-of-the-art performance among open-source models of comparable size, while running on a single NVIDIA DGX card!!
Open weights under the MIT license.
Coding
✅SWE-bench Verified: 0.845
✅TB2.1: 0.813
✅CyberGym: 0.800
✅NL2Repo: 0.512
Agentic
✅HLE: 0.446
✅BrowseComp: 0.785
✅MCP-Atlas: 0.746
✅Toolathlon: 0.708
🤗Hugging Face: huggingface.co/ornith-ai/Orn…
We can’t wait to see what you build with Ornith-1.5-122B.
Prithiv Sakthi retweeted
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!
Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.
🔗 github.com/deepseek-ai/DeepI…
1/4
Prithiv Sakthi retweeted
BOOM!
130K RAG claims verified by Jev!
Happy Sunday.
huggingface.co/datasets/Mazi…
Prithiv Sakthi retweeted
A 501B open model just landed on the Hub, and you can own it! Beam by @reflection_ai:
501B MoE, 23B active
1M token context
Built for coding + agents
Token Efficient
Apache 2.0
Day-0 in transformers, vLLM, SGLang. We also kicked the tyres hard on this, with shipped SFT + RL recipes 🧵
🤖 Made with AI
Prithiv Sakthi retweeted
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.
Prithiv Sakthi retweeted
🎆 Nemotron-3.5-Super-VL is here! 🎆
✅ Same base architecture as Super-3.0: 120B total, 12B active plus Vision encoder
✅ Ahead of Ultra-3.0 on most benchmarks! And now with visual reasoning!
✅ SWEBench-Pro 51.79%, AA index of 26 vs 23 for Ultra-3.0
Post-training pipeline is a greatly simplified and improved version of what we had for Ultra-3.0.
We reduced number of teachers, SFT set size while significantly improving data and environments quality and made it multimodal! 1/5
🤖 Made with AI
Prithiv Sakthi retweeted
Today, we’re expanding our Nemotron family of open models with Nemotron 3.5 Super VL.
Bringing visual understanding, reasoning, and tool use together to help AI agents complete more work in less time.
Open models ➡️ more control to customize, deploy, and build on your own terms.
Dive into what’s new:
Prithiv Sakthi retweeted
The recent Tokenizers v1 update seriously sped up tokenization for any NLP task, but now @SimonBrandeis is cooking another improvement, especially for BERT tokenizers:
an additional ~5x (or ~50x total from the previous tokenizers v0.23).
