Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Dive into Hunyuan-A13B, our latest open-source LLM built on an MoE architecture for optimal resource efficiency and high performance. Watch the video to discover its core strengths and how it provides a robust foundation for advancement across academic research, cost-effective AI solution development, and innovative application exploration. Try it...

TencentHunyuan's profile picture

Tencent HY

34,813 subscribers

44,270 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & TeknolojiHaberler & PolitikaEğitim
LIVE

Anya Rossi• Live Now

Private livecam show

10 Yorum

AshutoshShrivastava profil fotoğrafı
AshutoshShrivastava1 yıl önce

Really good for it's size and similar other models.

cedric profil fotoğrafı
cedric1 yıl önce

80B-A13B packs a punch! It’s a compact MoE that nails the balance between power and VRAM, plus it comes with 256k context. The benchmarks look great and go head-on with o1. This model is a gift for the community, and they even share benchmarks for the q8 and q4 quants.

Lasya Turiganti profil fotoğrafı
Lasya Turiganti1 yıl önce

@TencentHunyuan How can I use it in India ?

Aaliya profil fotoğrafı
Aaliya1 yıl önce

Love this

𝗭𝗲𝗻 𝗠𝗮𝗴𝗻𝗲𝘁𝘀 profil fotoğrafı
𝗭𝗲𝗻 𝗠𝗮𝗴𝗻𝗲𝘁𝘀1 yıl önce

Need compatibility with @lmstudio

Ai Lockup profil fotoğrafı
Ai Lockup1 yıl önce

We are willing to showcase it on our YouTube Channel ! Please Inbox for details.

John E profil fotoğrafı
John E1 yıl önce

Bro you guys are using an ai model to do your show case video, HIRE ME, I can run all English based publications and promos, and help you get a feel on English speaking vibe of your models and company, I will start for free

Prof Celso Fontes profil fotoğrafı
Prof Celso Fontes1 yıl önce

Such a pity there is no western api provider yet for this model

Lasya Turiganti profil fotoğrafı
Lasya Turiganti1 yıl önce

@TencentHunyuan Can I get access to This High Power in India 🥺 🫂

Rediminds, Inc profil fotoğrafı
Rediminds, Inc1 yıl önce

A13B is a timely proof that smart sparsity > brute-force scale. 3 active experts per token gives you near-70B quality on a single 80 GB GPU—the price/perf envelope most startups need for on-prem deployments. Curious to see how the FP8 + expert routing tricks translate to longer-context fine-tunes.

Benzer Videolar

HunyuanImage 3.0 is officially here. It's the first open-source model with industrial-grade native multimodal architecture and delivers instant, high-quality visual content for every designer and content creator. Watch this quick showcase to see its performance on generating intricate text, detailed comics, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:
1:33

HunyuanImage 3.0 is officially here. It's the first open-source model with industrial-grade native multimodal architecture and delivers instant, high-quality visual content for every designer and content creator. Watch this quick showcase to see its performance on generating intricate text, detailed comics, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

Tencent Hy

31,048 görüntüleme • 9 ay önce

🎬Dive into Hunyuan 3D 2.1, featuring high-precision geometry and PBR textures for stunningly realistic rendering. Get started with our comprehensive open-source package and tutorials⬇️ Model: Github: Hunyuan 3D Creation Engine:
0:36

🎬Dive into Hunyuan 3D 2.1, featuring high-precision geometry and PBR textures for stunningly realistic rendering. Get started with our comprehensive open-source package and tutorials⬇️ Model: Github: Hunyuan 3D Creation Engine:

Tencent Hy

29,454 görüntüleme • 1 yıl önce

Palantir AIP for Defense securely deploys the latest in LLM capabilities across environments — from classified networks to devices on the tactical edge. Discover how it enables responsible, effective, and compliant AI advantage. Coming soon:
1:11

Palantir AIP for Defense securely deploys the latest in LLM capabilities across environments — from classified networks to devices on the tactical edge. Discover how it enables responsible, effective, and compliant AI advantage. Coming soon:

Palantir

529,975 görüntüleme • 3 yıl önce

Meta FAIR recently released the Seamless Interaction Dataset, the largest known high-quality video dataset of its kind, with: 4,000+ diverse participants 4,000+ hours of footage 65k+ interactions 5,000+ annotated samples This dataset of full-body, in-person, face-to-face interaction videos represents a crucial stepping stone to understanding and modeling how people communicate and behave when they’re together—advancing AI's ability to generate more natural conversations and human-like gestures. Download the dataset on Hugging Face: Learn more about the dataset:
1:05

Meta FAIR recently released the Seamless Interaction Dataset, the largest known high-quality video dataset of its kind, with: 4,000+ diverse participants 4,000+ hours of footage 65k+ interactions 5,000+ annotated samples This dataset of full-body, in-person, face-to-face interaction videos represents a crucial stepping stone to understanding and modeling how people communicate and behave when they’re together—advancing AI's ability to generate more natural conversations and human-like gestures. Download the dataset on Hugging Face: Learn more about the dataset:

AI at Meta

23,836 görüntüleme • 11 ay önce

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:
2:09

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

Tencent Hy

412,658 görüntüleme • 9 ay önce

Introducing Chatterbox Multilingual 🌎 23 languages. One model. Open source. On GitHub , Hugging Face , and Let's dive in 🧵
0:31

Introducing Chatterbox Multilingual 🌎 23 languages. One model. Open source. On GitHub , Hugging Face , and Let's dive in 🧵

Resemble AI

24,082 görüntüleme • 10 ay önce

I'm thrilled to announce the launch of ⚡️Flash Diffusion from Jasper! Earlier this year, with our acquisition of Clipdrop, we launched the Jasper AI Research Lab in Paris. Today, we are excited to release our first piece of groundbreaking research: the open-source distillation method, "Flash Diffusion". Flash Diffusion accelerates inference by 500%, reduces computing costs, and produces higher-quality image outputs. Dive into the details and discover how Flash Diffusion is set to revolutionize the field of AI and image synthesis. Read all about it here: Try a demo on Hugging Face:
0:28

I'm thrilled to announce the launch of ⚡️Flash Diffusion from Jasper! Earlier this year, with our acquisition of Clipdrop, we launched the Jasper AI Research Lab in Paris. Today, we are excited to release our first piece of groundbreaking research: the open-source distillation method, "Flash Diffusion". Flash Diffusion accelerates inference by 500%, reduces computing costs, and produces higher-quality image outputs. Dive into the details and discover how Flash Diffusion is set to revolutionize the field of AI and image synthesis. Read all about it here: Try a demo on Hugging Face:

Timothy Young

10,093 görüntüleme • 2 yıl önce

🚀 Introducing the Earth Engine Dataset Explorer, powered by Google #Gemini! 🌍✨ Struggling to find the right #geospatial datasets for your research? Our Dataset Explorer recommends tailored datasets and offers an interactive exploration experience. 📹 Check out the video tutorial: 📒 Explore the notebook: #geemap #OpenSource #AI #EarthEngine
1:06

🚀 Introducing the Earth Engine Dataset Explorer, powered by Google #Gemini! 🌍✨ Struggling to find the right #geospatial datasets for your research? Our Dataset Explorer recommends tailored datasets and offers an interactive exploration experience. 📹 Check out the video tutorial: 📒 Explore the notebook: #geemap #OpenSource #AI #EarthEngine

Qiusheng Wu

23,939 görüntüleme • 1 yıl önce

We are live and kicking! For our latest project 1 dataset 100 visualizations, we challenged ourselves to turn one simple dataset into 100 insightful and visually appealing data visualizations. Explore all of the #dataviz and stories on
0:28

We are live and kicking! For our latest project 1 dataset 100 visualizations, we challenged ourselves to turn one simple dataset into 100 insightful and visually appealing data visualizations. Explore all of the #dataviz and stories on

ferdio

20,330 görüntüleme • 3 yıl önce

Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. **Just write a sentence describing the model you want.** A chain of AI systems will generate a dataset and train a model for you. And it's open-source:
1:01

Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. **Just write a sentence describing the model you want.** A chain of AI systems will generate a dataset and train a model for you. And it's open-source:

Matt Shumer

337,413 görüntüleme • 2 yıl önce

We’re also publicly releasing the Seamless Interaction Dataset, with 4,000+ participants and 4,000+ hours of interactions, making it the largest known video dataset of its kind. This dataset enables our audiovisual behavioral models to understand and generate human-like social behaviors, and represents a crucial stepping stone to understanding and modeling how people communicate and behave when they’re together. We’re sharing it here to help the research community advance their work:
0:20

We’re also publicly releasing the Seamless Interaction Dataset, with 4,000+ participants and 4,000+ hours of interactions, making it the largest known video dataset of its kind. This dataset enables our audiovisual behavioral models to understand and generate human-like social behaviors, and represents a crucial stepping stone to understanding and modeling how people communicate and behave when they’re together. We’re sharing it here to help the research community advance their work:

AI at Meta

11,956 görüntüleme • 1 yıl önce

Introducing `claude-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source.
0:42

Introducing `claude-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source.

Matt Shumer

383,130 görüntüleme • 2 yıl önce

We built a fully open-source dexterous robotic hand — for just $314. 🤖 Meet Aero Hand Open — precise, affordable, and built for embodied AI research. Watch it perform natural finger motions 👇 🔗 📘 Docs: 💻 GitHub: #robotics #opensource #AI #dexteroushand #embodiedAI
0:29

We built a fully open-source dexterous robotic hand — for just $314. 🤖 Meet Aero Hand Open — precise, affordable, and built for embodied AI research. Watch it perform natural finger motions 👇 🔗 📘 Docs: 💻 GitHub: #robotics #opensource #AI #dexteroushand #embodiedAI

Chestnut Robotics

58,023 görüntüleme • 9 ay önce

A major flagship addition to the open-source AI Models. Tencent has officially launched Hunyuan Hy3. This could be the most interesting open-source AI releases this year. ✓ 295B MoE architecture ✓ 21B active parameters ✓ 256K context ✓ Strong coding & reasoning ✓ Built for agent workflows ✓ Apache 2.0 license A big step forward for open AI infrastructure. Tencent Hy #Hy3 #Hunyuan #OpenSourceAI
0:48

A major flagship addition to the open-source AI Models. Tencent has officially launched Hunyuan Hy3. This could be the most interesting open-source AI releases this year. ✓ 295B MoE architecture ✓ 21B active parameters ✓ 256K context ✓ Strong coding & reasoning ✓ Built for agent workflows ✓ Apache 2.0 license A big step forward for open AI infrastructure. Tencent Hy #Hy3 #Hunyuan #OpenSourceAI

ZOYA ✪

17,363 görüntüleme • 4 gün önce

Check this!! Microsoft open-sourced a no-code data analysis tool. It's called Data Formulator and it provides AI-powered data analysis and an drag-and-drop UI for viz tasks. It also works beyond the initial dataset by creating relevant fields and the corresponding viz.
0:24

Check this!! Microsoft open-sourced a no-code data analysis tool. It's called Data Formulator and it provides AI-powered data analysis and an drag-and-drop UI for viz tasks. It also works beyond the initial dataset by creating relevant fields and the corresponding viz.

Avi Chawla

260,087 görüntüleme • 1 yıl önce

Meet Tencent HY-MT1.5 — our latest open-source translation models, featuring 1.8B and 7B models designed for seamless on-device and cloud deployment. 🌍 The 1.8B version is already trending at #1 on Hugging Face! 🥇It’s optimized for consumer hardware, delivering 0.18s latency (50 tokens) with just a 1GB memory footprint. Meanwhile, the 7B model achieves exceptional performance, surpassing many mid-sized models and rivaling the 90th percentile of Gemini 3.0 Pro. 🚀🧠 👉🏻 Try it now: 🔗 GitHub: 🤗 Hugging Face:
1:03

Meet Tencent HY-MT1.5 — our latest open-source translation models, featuring 1.8B and 7B models designed for seamless on-device and cloud deployment. 🌍 The 1.8B version is already trending at #1 on Hugging Face! 🥇It’s optimized for consumer hardware, delivering 0.18s latency (50 tokens) with just a 1GB memory footprint. Meanwhile, the 7B model achieves exceptional performance, surpassing many mid-sized models and rivaling the 90th percentile of Gemini 3.0 Pro. 🚀🧠 👉🏻 Try it now: 🔗 GitHub: 🤗 Hugging Face:

Tencent HY

17,105 görüntüleme • 6 ay önce

We are excited to unveil HunyuanVideo 1.5, the strongest open-source video generation model. Built upon DiT architecture, it redefines the open-source SOTA for accessibility and performance.🚀🚀🚀 HunyuanVideo 1.5 delivers state-of-the-art visual quality and motion coherence while drastically lowering the entry barrier for developers and creators: ⚡️ Unmatched Accessibility: Ultra-light 8.3B parameters, deployable on consumer GPUs with only 14GB VRAM. 🖥️ HD Cinematic Quality: Natively generates 5–10 second 480p/720p HD videos, with super-resolution support for 1080p cinematic quality. By merging SOTA performance with high hardware efficiency, HunyuanVideo 1.5 sets the new technical baseline for the open-source community. 🌐Project Page: 🔗Github: 🤗Hugging Face： 📄Technical Report:
1:03

We are excited to unveil HunyuanVideo 1.5, the strongest open-source video generation model. Built upon DiT architecture, it redefines the open-source SOTA for accessibility and performance.🚀🚀🚀 HunyuanVideo 1.5 delivers state-of-the-art visual quality and motion coherence while drastically lowering the entry barrier for developers and creators: ⚡️ Unmatched Accessibility: Ultra-light 8.3B parameters, deployable on consumer GPUs with only 14GB VRAM. 🖥️ HD Cinematic Quality: Natively generates 5–10 second 480p/720p HD videos, with super-resolution support for 1080p cinematic quality. By merging SOTA performance with high hardware efficiency, HunyuanVideo 1.5 sets the new technical baseline for the open-source community. 🌐Project Page: 🔗Github: 🤗Hugging Face： 📄Technical Report:

Tencent Hy

128,008 görüntüleme • 7 ay önce

Announcing Talkie: a new, open-weight historical LLM! We trained and finetuned a 13B model on a newly-curated dataset of only pre-1930 data. Try it below! with Alec Radford and Nick Levine 🧵
7:58

Announcing Talkie: a new, open-weight historical LLM! We trained and finetuned a 13B model on a newly-curated dataset of only pre-1930 data. Try it below! with Alec Radford and Nick Levine 🧵

David Duvenaud

1,455,958 görüntüleme • 2 ay önce

We previously shared our research on Layer Skip, an end-to-end solution for accelerating LLMs from researchers at Meta FAIR. It achieves this by executing a subset of an LLM’s layers and utilizing subsequent layers for verification and correction. We’re now releasing inference code and fine-tuned checkpoints for this work. Model weights on Hugging Face ➡️ More details ➡️ We hope that releasing this work will open up new areas of experimentation and innovative new research in optimization and interpretability.
1:12

We previously shared our research on Layer Skip, an end-to-end solution for accelerating LLMs from researchers at Meta FAIR. It achieves this by executing a subset of an LLM’s layers and utilizing subsequent layers for verification and correction. We’re now releasing inference code and fine-tuned checkpoints for this work. Model weights on Hugging Face ➡️ More details ➡️ We hope that releasing this work will open up new areas of experimentation and innovative new research in optimization and interpretability.

AI at Meta

156,598 görüntüleme • 1 yıl önce