Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Today, every Nomic-Embed-Text embedding becomes multimodal. Introducing Nomic-Embed-Vision: - a high quality, unified embedding space for image, text, and multimodal tasks - outperforms both OpenAI CLIP and text-embedding-3-small - open weights and code to enable indie hacking, research, and experimentation - released in collaboration with MongoDB, LlamaIndex 🦙, ,... show more

CalCo

20,569 subscribers

103,204 görüntüleme • 2 yıl önce •via X (Twitter)

Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

11 Yorum

Nomic AI profil fotoğrafı

Nomic AI2 yıl önce

Existing text-image embedding models, including OpenAI’s CLIP, dramatically underperform specialized text encoders on text retrieval tasks. This forces developers to deploy several embedding models and store several vector indices for multimodal applications. With Nomic-Embed-Vision, developers can use a single vector space to power both their text-text and text-image retrieval tasks.

Nomic AI profil fotoğrafı

Nomic AI2 yıl önce

We’ve been honored by the reception of Nomic-Embed-Text, which has grown into one of the most downloaded models on @huggingface. We designed Nomic-Embed-Vision to be compatible with Nomic-Embed-Text out of the box, making it easy for developers using Nomic-Embed-Text to extend their applications with multimodal features. Put simply, any vector created using Nomic-Embed-Text can be used to query vectors created by Nomic-Embed-Vision, and vice versa.

Nomic AI profil fotoğrafı

Nomic AI2 yıl önce

We are releasing Nomic-Embed-Vision under a CC-BY-NC-4.0 license. This will enable researchers and hackers to continue experimenting with our models, as well as enable Nomic to continue releasing great models in the future. As Nomic releases future models, we intend to apply Apache-2.0 licenses to the less recent models in our catalogue. You can download the model on @huggingface here!

Nomic AI profil fotoğrafı

Nomic AI2 yıl önce

We also worked with @LangChainAI and @llama_index to ensure day 1 compatibility with the model orchestration frameworks developers love:

Nomic AI profil fotoğrafı

Nomic AI2 yıl önce

If you want to use Nomic-Embed-Vision or Nomic-Embed-Text in production, we recommend using our @awscloud marketplace offering, and storing the vectors in a @MongoDB Atlas vector store:

Nomic AI profil fotoğrafı

Nomic AI2 yıl önce

You can also access the model through our python client and in our Nomic Embedding API.

Nomic AI profil fotoğrafı

Nomic AI2 yıl önce

To learn more about how we built Nomic-Embed-Vision, check out our blog post, and keep an eye out for our forthcoming technical report:

Nomic AI profil fotoğrafı

Nomic AI2 yıl önce

Nomic Embed was trained on @digitalocean compute, with early experiments made possible by a generous compute grant from @LambdaAPI.

andrew gao profil fotoğrafı

andrew gao2 yıl önce

I got early access and built this using Nomic-Embed-Vision! Check out a museum collection of 250,000 works of art!

txh 📟 profil fotoğrafı

txh 📟2 yıl önce

@Teknium1 this is really cool, what can I use to visualize/plot the cluster after computing the embeddings?

Nomic AI profil fotoğrafı

Nomic AI2 yıl önce

@Teknium1 You can use

Benzer Videolar

DeepSeek RAG Agent : 100% Local using ollama Code below 👇 💡 RAG AI Agent with Reasoning DeepSeek 🌐 Local using @Ollama ✨ Few lines of Code PraisonAI 🔍 UI using Streamlit 💪 Nomic Embed Text for embedding 🧠 Deep Contextual Awareness

DeepSeek RAG Agent : 100% Local using ollama Code below 👇 💡 RAG AI Agent with Reasoning DeepSeek 🌐 Local using @Ollama ✨ Few lines of Code PraisonAI 🔍 UI using Streamlit 💪 Nomic Embed Text for embedding 🧠 Deep Contextual Awareness

Mervin Praison

59,593 görüntüleme • 1 yıl önce

Say hello to multi-element embedding for the web. 👋 Flutter 3.24 builds on top of element embedding and now lets you embed multiple Flutter views within a host web app.

Say hello to multi-element embedding for the web. 👋 Flutter 3.24 builds on top of element embedding and now lets you embed multiple Flutter views within a host web app.

Flutter

15,297 görüntüleme • 1 yıl önce

Embedding features learned with sparse autoencoders can make semantic edits to text ✨ (+ a reading/highlighting demo) I've built an interface to explore and visualize GPT-4 labelled features learned from a text embedding model's latent space. Here's a little video, more in 👇

Embedding features learned with sparse autoencoders can make semantic edits to text ✨ (+ a reading/highlighting demo) I've built an interface to explore and visualize GPT-4 labelled features learned from a text embedding model's latent space. Here's a little video, more in 👇

Linus

51,614 görüntüleme • 2 yıl önce

Build a Vision RAG app with Gemini 2.5 Flash and Cohere Multimodal Embedding that can understand images and diagrams in PDF. 100% Opensource code with step-by-step tutorial.

Build a Vision RAG app with Gemini 2.5 Flash and Cohere Multimodal Embedding that can understand images and diagrams in PDF. 100% Opensource code with step-by-step tutorial.

Shubham Saboo

60,638 görüntüleme • 1 yıl önce

Llama 3.2 features 11B & 90B models, our first multimodal Llama models with support for vision tasks. These models can take in both image and text prompts to deeply understand and reason on inputs.

Llama 3.2 features 11B & 90B models, our first multimodal Llama models with support for vision tasks. These models can take in both image and text prompts to deeply understand and reason on inputs.

AI at Meta

121,502 görüntüleme • 1 yıl önce

jina-embeddings-v5-omni is here! Our first universal embedding model for text, images, audio, and video. Available in two sizes: small (1.57B, 1024-dim, 32K context) and nano (0.95B, 768-dim, 8K context). Both support Matryoshka truncation down to 32 dimensions. v5-omni is back-compatible: if you already use jina-embeddings-v5-text-small/nano, the existing text indexes work with v5-omni out of the box. Without reindexing the text, just index your multimodal content with v5-omni and start searching images, audio, and video.

jina-embeddings-v5-omni is here! Our first universal embedding model for text, images, audio, and video. Available in two sizes: small (1.57B, 1024-dim, 32K context) and nano (0.95B, 768-dim, 8K context). Both support Matryoshka truncation down to 32 dimensions. v5-omni is back-compatible: if you already use jina-embeddings-v5-text-small/nano, the existing text indexes work with v5-omni out of the box. Without reindexing the text, just index your multimodal content with v5-omni and start searching images, audio, and video.

Jina AI

130,989 görüntüleme • 25 gün önce

GLM-4.6V can accept multimodal inputs of various types and automatically generate high-quality, structured image-text interleaved content.

GLM-4.6V can accept multimodal inputs of various types and automatically generate high-quality, structured image-text interleaved content.

Z.ai

13,655 görüntüleme • 6 ay önce

Start building with Gemini Embedding 2, our most capable and first fully multimodal embedding model built on the Gemini architecture. Now available in preview via the Gemini API and in Vertex AI.

Start building with Gemini Embedding 2, our most capable and first fully multimodal embedding model built on the Gemini architecture. Now available in preview via the Gemini API and in Vertex AI.

Google AI Developers

30,483,135 görüntüleme • 2 ay önce

StarVector is out on Hugging Face StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.

StarVector is out on Hugging Face StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.

AK

254,173 görüntüleme • 1 yıl önce

[CLIP] by Hand ✍️ The CLIP (Contrastive Language–Image Pre-training) model, a groundbreaking work by OpenAI, redefines the intersection of computer vision and natural language processing. It is the basis of all the multi-modal foundation models we see today. How does CLIP work? Goal: 🟨 Learn a shared embedding space for text and image [1] Given ↳ A mini batch of 3 text-image pairs ↳ OpenAI used 400 million text-image pairs to train its original CLIP model. Process 1st pair: "big table" [2] 🟪 Text → 2 Vectors (3D) ↳ Look up word embedding vectors using word2vec. [3] 🟩 Image → 2 Vectors (4D) ↳ Divide the image into two patches. ↳ Flatten each patch [4] Process other pairs ↳ Repeat [2]-[3] [5] 🟪 Text Encoder & 🟩 Image Encoder ↳ Encode input vectors into feature vectors ↳ Here, both encoders are simple one layer perceptron (linear + ReLU) ↳ In practice, the encoders are usually transformer models. [6] 🟪 🟩 Mean Pooling: 2 → 1 vector ↳ Average 2 feature vectors into a single vector by averaging across the columns ↳ The goal is to have one vector to represent each image or text [7] 🟪 🟩 -> 🟨 Projection ↳ Note that the text and image feature vectors from the encoders have different dimensions (3D vs. 4D). ↳ Use a linear layer to project image and text vectors to a 2D shared embedding space. 🏋️ Contrastive Pre-training 🏋️ [8] Prepare for MatMul ↳ Copy text vectors (T1,T2,T3) ↳ Copy the transpose of image vectors (I1,I2,I3) ↳ They are all in the 2D shared embedding space. [9] 🟦 MatMul ↳ Multiply T and I matrices. ↳ This is equivalent to taking dot product between every pair of image and text vectors. ↳ The purpose is to use dot product to estimate the similarity between a pair of image-text. [10] 🟦 Softmax: e^x ↳ Raise e to the power of the number in each cell ↳ To simplify hand calculation, we approximate e^□ with 3^□. [11] 🟦 Softmax: ∑ ↳ Sum each row for 🟩 image→🟪 text ↳ Sum each column for 🟪 text→ 🟩 image [12] 🟦 Softmax: 1 / sum ↳ Divide each element by the column sum to obtain a similarity matrix for 🟪 text→🟩 image ↳ Divide each element by the row sum to obtain a similarity matrix for 🟩 image→🟪 text [13] 🟥 Loss Gradients ↳ The "Targets" for the similarity matrices are Identity Matrices. ↳ Why? If I and T come from the same pair (i=j), we want the highest value, which is 1, and 0 otherwise. ↳ Apply the simple equation of [Similarity - Target] to compute gradients of for both directions. ↳ Why so simple? Because when Softmax and Cross-Entropy Loss are used together, the math magically works out that way. ↳ These gradients kick off the backpropagation process to update weights and biases of the encoders and projection layers (red borders).

[CLIP] by Hand ✍️ The CLIP (Contrastive Language–Image Pre-training) model, a groundbreaking work by OpenAI, redefines the intersection of computer vision and natural language processing. It is the basis of all the multi-modal foundation models we see today. How does CLIP work? Goal: 🟨 Learn a shared embedding space for text and image [1] Given ↳ A mini batch of 3 text-image pairs ↳ OpenAI used 400 million text-image pairs to train its original CLIP model. Process 1st pair: "big table" [2] 🟪 Text → 2 Vectors (3D) ↳ Look up word embedding vectors using word2vec. [3] 🟩 Image → 2 Vectors (4D) ↳ Divide the image into two patches. ↳ Flatten each patch [4] Process other pairs ↳ Repeat [2]-[3] [5] 🟪 Text Encoder & 🟩 Image Encoder ↳ Encode input vectors into feature vectors ↳ Here, both encoders are simple one layer perceptron (linear + ReLU) ↳ In practice, the encoders are usually transformer models. [6] 🟪 🟩 Mean Pooling: 2 → 1 vector ↳ Average 2 feature vectors into a single vector by averaging across the columns ↳ The goal is to have one vector to represent each image or text [7] 🟪 🟩 -> 🟨 Projection ↳ Note that the text and image feature vectors from the encoders have different dimensions (3D vs. 4D). ↳ Use a linear layer to project image and text vectors to a 2D shared embedding space. 🏋️ Contrastive Pre-training 🏋️ [8] Prepare for MatMul ↳ Copy text vectors (T1,T2,T3) ↳ Copy the transpose of image vectors (I1,I2,I3) ↳ They are all in the 2D shared embedding space. [9] 🟦 MatMul ↳ Multiply T and I matrices. ↳ This is equivalent to taking dot product between every pair of image and text vectors. ↳ The purpose is to use dot product to estimate the similarity between a pair of image-text. [10] 🟦 Softmax: e^x ↳ Raise e to the power of the number in each cell ↳ To simplify hand calculation, we approximate e^□ with 3^□. [11] 🟦 Softmax: ∑ ↳ Sum each row for 🟩 image→🟪 text ↳ Sum each column for 🟪 text→ 🟩 image [12] 🟦 Softmax: 1 / sum ↳ Divide each element by the column sum to obtain a similarity matrix for 🟪 text→🟩 image ↳ Divide each element by the row sum to obtain a similarity matrix for 🟩 image→🟪 text [13] 🟥 Loss Gradients ↳ The "Targets" for the similarity matrices are Identity Matrices. ↳ Why? If I and T come from the same pair (i=j), we want the highest value, which is 1, and 0 otherwise. ↳ Apply the simple equation of [Similarity - Target] to compute gradients of for both directions. ↳ Why so simple? Because when Softmax and Cross-Entropy Loss are used together, the math magically works out that way. ↳ These gradients kick off the backpropagation process to update weights and biases of the encoders and projection layers (red borders).

Tom Yeh

67,790 görüntüleme • 2 yıl önce

[1/n] Do distinct large models admit a simple map that aligns their embedding spaces? We show that across multimodal contrastive models—trained on different data and architectures—an orthogonal map aligns image embeddings. Strikingly, the same map also aligns text embeddings.

[1/n] Do distinct large models admit a simple map that aligns their embedding spaces? We show that across multimodal contrastive models—trained on different data and architectures—an orthogonal map aligns image embeddings. Strikingly, the same map also aligns text embeddings.

Sharut Gupta

36,746 görüntüleme • 3 ay önce

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,257 görüntüleme • 9 ay önce

i can now search my entire ad library by concept. "ugc testimonials with urgency hooks" and it just finds them. here's how i built it: searchable ad swipe file > drag in creatives > AI analyzes them > search by concept > find anything in seconds -> uses google's new multimodal embedding model. images, video, and text all searchable together. -> type "ugc testimonials with urgency hooks" and it finds them. no manual tags needed. -> every ad gets auto-analyzed by gemini on import. hook type, structure, audience, CTA. all searchable. -> dual-vector scoring. visual embedding + text embedding. takes the stronger signal. full build breakdown in video + notion guide in the comments

i can now search my entire ad library by concept. "ugc testimonials with urgency hooks" and it just finds them. here's how i built it: searchable ad swipe file > drag in creatives > AI analyzes them > search by concept > find anything in seconds -> uses google's new multimodal embedding model. images, video, and text all searchable together. -> type "ugc testimonials with urgency hooks" and it finds them. no manual tags needed. -> every ad gets auto-analyzed by gemini on import. hook type, structure, audience, CTA. all searchable. -> dual-vector scoring. visual embedding + text embedding. takes the stronger signal. full build breakdown in video + notion guide in the comments

J.B.

27,000 görüntüleme • 2 ay önce

Launching the 1st Arena for Embedding Models: MTEB Arena🏟️ Vote @ ⚔️ 15 Models: OpenAI Google Cohere Voyage_AI_ Jina AI Salesforce AI Research Nomic E5 GritLM BGE.. 3 Tasks: Retrieval/Clustering/STS Deep dive with me on embeddings & the arena👇 🧵1/13

Launching the 1st Arena for Embedding Models: MTEB Arena🏟️ Vote @ ⚔️ 15 Models: OpenAI Google Cohere Voyage_AI_ Jina AI Salesforce AI Research Nomic E5 GritLM BGE.. 3 Tasks: Retrieval/Clustering/STS Deep dive with me on embeddings & the arena👇 🧵1/13

Niklas Muennighoff

58,942 görüntüleme • 1 yıl önce

1/ Introducing Lynx - the leading hallucination detection model 🚀👀 - Beats GPT-4o on hallucination tasks - Open source, open weights, open data - Excels in real-world domains like medicine and finance We are excited to launch Lynx with Day 1 integration partners: NVIDIA, MongoDB, and Nomic 🔥

1/ Introducing Lynx - the leading hallucination detection model 🚀👀 - Beats GPT-4o on hallucination tasks - Open source, open weights, open data - Excels in real-world domains like medicine and finance We are excited to launch Lynx with Day 1 integration partners: NVIDIA, MongoDB, and Nomic 🔥

PatronusAI

81,446 görüntüleme • 1 yıl önce

We’re expanding the Gemini API File Search tool 🔍 with 3 new updates that enable developers to more easily build multimodal RAG systems with enhanced precision: + Multimodal Support: By leveraging our Gemini Embedding 2 model, File Search can now reason across image and text simultaneously. + Custom Metadata Filtering: Bring structure to unstructured data by tagging files with custom key-value labels. This pre-filters your data and boosts search speed. + Exact citations: File Search can now capture and return the exact source (down to the page number) for every piece of information indexed. See multimodal File Search in action with our example app in Google AI Studio. Chat with your entire image and doc library, ask questions, and trace answers back to the source:

We’re expanding the Gemini API File Search tool 🔍 with 3 new updates that enable developers to more easily build multimodal RAG systems with enhanced precision: + Multimodal Support: By leveraging our Gemini Embedding 2 model, File Search can now reason across image and text simultaneously. + Custom Metadata Filtering: Bring structure to unstructured data by tagging files with custom key-value labels. This pre-filters your data and boosts search speed. + Exact citations: File Search can now capture and return the exact source (down to the page number) for every piece of information indexed. See multimodal File Search in action with our example app in Google AI Studio. Chat with your entire image and doc library, ask questions, and trace answers back to the source:

Google AI Developers

107,790 görüntüleme • 1 ay önce

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:

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

31,033 görüntüleme • 8 ay önce

NEW: Perplexity just released pplx-embed, a series of powerful embedding models. Inspired by their logo, I built a small semantic search demo: enter a query and the model retrieves the most relevant page. Everything runs locally in your browser with Transformers.js and Three.js

Xenova

10,983 görüntüleme • 3 ay önce

Today we released Meta Spirit LM — our first open source multimodal language model that freely mixes text and speech. Many existing AI voice experiences today use ASR to techniques to process speech before synthesizing with an LLM to generate text — but these approaches compromise the expressive aspects of speech. Using phonetic, pitch and tone tokens, Spirit LM models can overcome these limitations for both inputs and outputs to generate more natural sounding speech while also learning new tasks across ASR, TTS and speech classification. We hope that sharing this work will enable the research community to further new approaches for text and speech integration.

Today we released Meta Spirit LM — our first open source multimodal language model that freely mixes text and speech. Many existing AI voice experiences today use ASR to techniques to process speech before synthesizing with an LLM to generate text — but these approaches compromise the expressive aspects of speech. Using phonetic, pitch and tone tokens, Spirit LM models can overcome these limitations for both inputs and outputs to generate more natural sounding speech while also learning new tasks across ASR, TTS and speech classification. We hope that sharing this work will enable the research community to further new approaches for text and speech integration.

AI at Meta

351,589 görüntüleme • 1 yıl önce