Hugging Face (Twitter)
RT @SOSOHAJALAB: $9 / month can do everythings in @huggingface ❤️ https://twitter.com/victormustar/status/1960422110527926766#m
RT @SOSOHAJALAB: $9 / month can do everythings in @huggingface ❤️ https://twitter.com/victormustar/status/1960422110527926766#m
This media is not supported in your browser
VIEW IN TELEGRAM
Hugging Face (Twitter)
RT @Alibaba_Wan: 🚀Introducing Wan2.2-S2V — a 14B parameter model designed for film-grade, audio-driven human animation. 🎬Going beyond basic talking heads to deliver professional-level quality for film, TV, and digital content. And it’s open-source!
✨ Key features:
🔹 Long-video dynamic consistency
🔹 Cinema-quality audio-to-video generation
🔹 Advanced motion and environment control via instruction
Perfect for filmmakers, content creators, and developers crafting immersive AI-powered stories.
Try it now : wan.video/
Github: github.com/Wan-Video/Wan2.2
Project: https://humanaigc.github.io/wan-s2v-webpage
Hugging Face Demo: https://huggingface.co/spaces/Wan-AI/Wan2.2-S2V
Modelscope Demo: https://www.modelscope.cn/studios/Wan-AI/Wan2.2-S2V
Hugging Face Weights: https://huggingface.co/Wan-AI/Wan2.2-S2V-14B
ModelScope Weights: https://www.modelscope.cn/models/Wan-AI/Wan2.2-S2V-14B
RT @Alibaba_Wan: 🚀Introducing Wan2.2-S2V — a 14B parameter model designed for film-grade, audio-driven human animation. 🎬Going beyond basic talking heads to deliver professional-level quality for film, TV, and digital content. And it’s open-source!
✨ Key features:
🔹 Long-video dynamic consistency
🔹 Cinema-quality audio-to-video generation
🔹 Advanced motion and environment control via instruction
Perfect for filmmakers, content creators, and developers crafting immersive AI-powered stories.
Try it now : wan.video/
Github: github.com/Wan-Video/Wan2.2
Project: https://humanaigc.github.io/wan-s2v-webpage
Hugging Face Demo: https://huggingface.co/spaces/Wan-AI/Wan2.2-S2V
Modelscope Demo: https://www.modelscope.cn/studios/Wan-AI/Wan2.2-S2V
Hugging Face Weights: https://huggingface.co/Wan-AI/Wan2.2-S2V-14B
ModelScope Weights: https://www.modelscope.cn/models/Wan-AI/Wan2.2-S2V-14B
Hugging Face (Twitter)
RT @reach_vb: LETS GOOO! 2,000,000+ PUBLIC REPOS ON THE HUB 🔥
from 100K to 2M in the last couple years has been surreal - onwards and upwards! 🤗
RT @reach_vb: LETS GOOO! 2,000,000+ PUBLIC REPOS ON THE HUB 🔥
from 100K to 2M in the last couple years has been surreal - onwards and upwards! 🤗
Hugging Face (Twitter)
RT @HaixuanT: Worked 9 month on building AV1 codec for AI and robotics and this is what I learned for streaming, training, and storage!
Detailed report here:
RT @HaixuanT: Worked 9 month on building AV1 codec for AI and robotics and this is what I learned for streaming, training, and storage!
Detailed report here:
huggingface.co
AV1 for robotics AI streaming, training and storage.
A Blog post by haixuan tao on Hugging Face
Hugging Face (Twitter)
RT @victormustar: Another OpenAI release on Hugging Face 👀
https://huggingface.co/datasets/openai/healthbench
RT @victormustar: Another OpenAI release on Hugging Face 👀
https://huggingface.co/datasets/openai/healthbench
huggingface.co
openai/healthbench · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face (Twitter)
RT @Thom_Wolf: Little know fact I realized talking with a researcher: the explosion of action-controlled World Models is also powered by strongly improved open-source video models.
Again open-source is enabling teams to explore, tweak and share mind blowing new use-cases far from original idea
RT @Thom_Wolf: Little know fact I realized talking with a researcher: the explosion of action-controlled World Models is also powered by strongly improved open-source video models.
Again open-source is enabling teams to explore, tweak and share mind blowing new use-cases far from original idea
Hugging Face (Twitter)
RT @NVIDIAAIDev: Ranked #1 on @Meta's Physical Reasoning Leaderboard on @huggingface for a reason. 👏 🔥 🏆
Cosmos Reason enables robots and AI agents to reason like humans by leveraging prior knowledge, physics, and common sense to intelligently interact with the real world.
This state-of-the-art reasoning VLM excels in physical AI applications like:
📊 Data curation and annotation
🤖 Robot planning and reasoning
▶️ Video analytics AI agents
See the leaderboard → nvda.ws/4mLUmjd
Check out Cosmos Reason → nvda.ws/425mMfF
RT @NVIDIAAIDev: Ranked #1 on @Meta's Physical Reasoning Leaderboard on @huggingface for a reason. 👏 🔥 🏆
Cosmos Reason enables robots and AI agents to reason like humans by leveraging prior knowledge, physics, and common sense to intelligently interact with the real world.
This state-of-the-art reasoning VLM excels in physical AI applications like:
📊 Data curation and annotation
🤖 Robot planning and reasoning
▶️ Video analytics AI agents
See the leaderboard → nvda.ws/4mLUmjd
Check out Cosmos Reason → nvda.ws/425mMfF
Hugging Face (Twitter)
RT @mervenoyann: MiniCPM-V 4.5 is very good! 🤗
it comes with hybrid thinking: it decides when to think on it's own 😍
it also can handle high res documents with odd aspect ratios, and super long videos efficiently 🙏🏻
see below hybrid results ⤵️ model is in comments!
RT @mervenoyann: MiniCPM-V 4.5 is very good! 🤗
it comes with hybrid thinking: it decides when to think on it's own 😍
it also can handle high res documents with odd aspect ratios, and super long videos efficiently 🙏🏻
see below hybrid results ⤵️ model is in comments!
Hugging Face (Twitter)
RT @elonmusk: It’s a good model, sir https://twitter.com/victormustar/status/1960613514562752685#m
RT @elonmusk: It’s a good model, sir https://twitter.com/victormustar/status/1960613514562752685#m
Hugging Face (Twitter)
RT @ArtificialAnlys: NVIDIA has released Nemotron Nano 9B V2, a small 9B reasoning model that scores 43 on the Artificial Analysis Intelligence Index, the highest yet for <10B models
Nemotron 9B V2 is the first Nemotron model pre-trained by @NVIDIA. Previous Nemotron models have been developed by post-training on Meta Llama models.
Architecture & Training: The model uses a hybrid Mamba-Transformer architecture. NVIDIA pre-trained a 12B parameter base model and applied post-training with a range of techniques including RLHF and GRPO. The final 9B size was pruned from this model and re-trained with the base model as a teacher.
Small-model frontier: with only 9B parameters, Nemotron Nano 9B V2 is placed ahead of Llama 4 Maverick on our leaderboard, equal to Solar Pro 2 with reasoning and trails just behind gpt-oss-20B (high).
Along with this model, NVIDIA rele...
Перейти на оригинальный пост
RT @ArtificialAnlys: NVIDIA has released Nemotron Nano 9B V2, a small 9B reasoning model that scores 43 on the Artificial Analysis Intelligence Index, the highest yet for <10B models
Nemotron 9B V2 is the first Nemotron model pre-trained by @NVIDIA. Previous Nemotron models have been developed by post-training on Meta Llama models.
Architecture & Training: The model uses a hybrid Mamba-Transformer architecture. NVIDIA pre-trained a 12B parameter base model and applied post-training with a range of techniques including RLHF and GRPO. The final 9B size was pruned from this model and re-trained with the base model as a teacher.
Small-model frontier: with only 9B parameters, Nemotron Nano 9B V2 is placed ahead of Llama 4 Maverick on our leaderboard, equal to Solar Pro 2 with reasoning and trails just behind gpt-oss-20B (high).
Along with this model, NVIDIA rele...
Перейти на оригинальный пост
Hugging Face (Twitter)
RT @rohanpaul_ai: 🖼️ MiniCPM-V 4.5 just dropped on @huggingface
Apache 2 with free commercial use.
With only 8B parameters, it surpasses many SOTA models like GPT-4o-latest, Gemini-2.0 Pro, Qwen2.5-VL 72B for vision-language capabilities, making it the most performant MLLM under 30B parameters.
- combines strong vision, fast video handling, and tough OCR, so the headline is real capability with small compute.
- High resolution images up to 1.8M pixels pass through an LLaVA-UHD style path that uses 4x fewer visual tokens, which is why reading small text and dense PDFs holds up.
- The model pairs Qwen3-8B as the language core with a SigLIP2-400M vision tower, giving it a compact but capable backbone.
- On public leaderboards it posts 77.0 on OpenCompass, hits 2500 on MME, and leads document tasks like OCRBench 89.0, with strong video numbers on Video-MME, LVBench, and MLVU.
- A new unified 3D-Resampler packs 6 consecutive 448x448 frames into 64...
Перейти на оригинальный пост
RT @rohanpaul_ai: 🖼️ MiniCPM-V 4.5 just dropped on @huggingface
Apache 2 with free commercial use.
With only 8B parameters, it surpasses many SOTA models like GPT-4o-latest, Gemini-2.0 Pro, Qwen2.5-VL 72B for vision-language capabilities, making it the most performant MLLM under 30B parameters.
- combines strong vision, fast video handling, and tough OCR, so the headline is real capability with small compute.
- High resolution images up to 1.8M pixels pass through an LLaVA-UHD style path that uses 4x fewer visual tokens, which is why reading small text and dense PDFs holds up.
- The model pairs Qwen3-8B as the language core with a SigLIP2-400M vision tower, giving it a compact but capable backbone.
- On public leaderboards it posts 77.0 on OpenCompass, hits 2500 on MME, and leads document tasks like OCRBench 89.0, with strong video numbers on Video-MME, LVBench, and MLVU.
- A new unified 3D-Resampler packs 6 consecutive 448x448 frames into 64...
Перейти на оригинальный пост