正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Announcing llama-ocr – a free + open source OCR tool! It takes documents (images for now) & outputs markdown, and does really well for complex receipts, PDFs with tables/charts, ect... Powered by Llama 3.2 vision on Together AI & available on npm today!

Hassan

96,798 subscribers

443,761 次观看 • 1 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Announcing PicMenu – a free & open source menu visualizer! It takes a restaurant menu picture and generates nice images for each dish, and works great for lots of non-english menus too. Powered by Llama 3.2 vision + Flux on Together AI & available today!

Announcing PicMenu – a free & open source menu visualizer! It takes a restaurant menu picture and generates nice images for each dish, and works great for lots of non-english menus too. Powered by Llama 3.2 vision + Flux on Together AI & available today!

Hassan

77,023 次观看 • 1 年前

🔥 New on File to Markdown ⚡ Drop any file → get clean, AI-ready Markdown back. 📄 PDFs, DOCX, ODT 📊 Excel, Numbers, CSV 🖼 Images (AI-powered OCR + summarization) Upload or paste a URL. API included, no key needed. Free. No signup. Details:

🔥 New on File to Markdown ⚡ Drop any file → get clean, AI-ready Markdown back. 📄 PDFs, DOCX, ODT 📊 Excel, Numbers, CSV 🖼 Images (AI-powered OCR + summarization) Upload or paste a URL. API included, no key needed. Free. No signup. Details:

Emre Elbeyoglu

113,666 次观看 • 3 个月前

Llama 3.2 is the latest open-source AI model from Meta, released only a few hours ago. Here is the 3B parameter model running on Akash Chat at 165 tokens/second, powered by NVIDIA A100s on Akash. Try Llama 3.2 for free, no sign-in required:

Llama 3.2 is the latest open-source AI model from Meta, released only a few hours ago. Here is the 3B parameter model running on Akash Chat at 165 tokens/second, powered by NVIDIA A100s on Akash. Try Llama 3.2 for free, no sign-in required:

Akash Network

37,087 次观看 • 1 年前

I just created my own LaTeX-OCR app using Llama 3.2 Vision! Upload the LaTeX code as an image, and it gives you the corresponding LaTeX code using Llama 3.2 multimodal! Here's what I used: - Ollama for serving Llama 3.2 vision locally - Streamlit for the UI Everything is just 50 lines of code! Find the code in the next tweet. -- Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs. Find me → Avi Chawla

I just created my own LaTeX-OCR app using Llama 3.2 Vision! Upload the LaTeX code as an image, and it gives you the corresponding LaTeX code using Llama 3.2 multimodal! Here's what I used: - Ollama for serving Llama 3.2 vision locally - Streamlit for the UI Everything is just 50 lines of code! Find the code in the next tweet. -- Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs. Find me → Avi Chawla

Avi Chawla

15,608 次观看 • 1 年前

Everyone is sleeping on this new OCR model! Datalab's Chandra topped independent benchmarks and beat the previous best dots-ocr. - Supports 40+ languages - Extracts complex texts, tables, formulas easily I tested on Ramanujan's handwritten letter from 1913. 100% open-source.

Everyone is sleeping on this new OCR model! Datalab's Chandra topped independent benchmarks and beat the previous best dots-ocr. - Supports 40+ languages - Extracts complex texts, tables, formulas easily I tested on Ramanujan's handwritten letter from 1913. 100% open-source.

Avi Chawla

158,386 次观看 • 5 个月前

Llama 2: Now on Hugging Chat 🤗🦙 Try out the 70B Chat model for free with super fast inference, web search, and powered by open-source tools! 👉

Llama 2: Now on Hugging Chat 🤗🦙 Try out the 70B Chat model for free with super fast inference, web search, and powered by open-source tools! 👉

Hugging Face

403,519 次观看 • 2 年前

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

Jafar Najafov

13,630 次观看 • 2 个月前

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

A peanut-sized Chinese model just dethroned Gemini at reading documents. GLM-OCR is a 0.9B parameter vision-language model. It scores 94.62 on OmniDocBench V1.5, ranking #1 overall. For context, it outperforms models 100x its size. 100% open-source. It works in two stages. 1. A layout engine detects every region in a document. 2. Each region gets read in parallel. The model predicts multiple tokens per step instead of one. That's what makes it so fast at small size. It handles things most OCR tools struggle with: > Complex tables and nested layouts > Handwritten text and stamps > Math formulas and code blocks > Mixed image-and-text documents You can run it locally through Ollama. It fits on edge devices with limited compute. Every expensive OCR API just got a free competitor.

AlphaSignal AI

91,680 次观看 • 2 个月前

This peanut-sized chinese model just dethroned Gemini at reading documents. It’s called glm-ocr. it’s a tiny 0.9b parameter vision-language model that is about to replace every expensive ocr api you use. → Handles text, tables, formulas, handwriting → Scored 94.62 on OmniDocBench V1.5 → 8 languages → vLLM, SGLang, Ollama And it’s 100% open-source.

This peanut-sized chinese model just dethroned Gemini at reading documents. It’s called glm-ocr. it’s a tiny 0.9b parameter vision-language model that is about to replace every expensive ocr api you use. → Handles text, tables, formulas, handwriting → Scored 94.62 on OmniDocBench V1.5 → 8 languages → vLLM, SGLang, Ollama And it’s 100% open-source.

Alvaro Cintas

37,477 次观看 • 2 个月前

GutenOCR: A Grounded Vision-Language Front-End for Documents Fine-tunes Qwen2.5-VL-3B and 7B using a grounded OCR evaluation protocol, substantially improving region- and line-level OCR as well as text-detection recall

GutenOCR: A Grounded Vision-Language Front-End for Documents Fine-tunes Qwen2.5-VL-3B and 7B using a grounded OCR evaluation protocol, substantially improving region- and line-level OCR as well as text-detection recall

Niels Rogge

45,811 次观看 • 4 个月前

You can now run inference directly on the Llama 4 Hugging Face model page – powered by Together AI!

You can now run inference directly on the Llama 4 Hugging Face model page – powered by Together AI!

Together AI

21,489 次观看 • 1 年前

Today we’re releasing Code Llama, a large language model built on top of Llama 2, fine-tuned for coding & state-of-the-art for publicly available coding tools. Keeping with our open approach, Code Llama is publicly-available now for both research & commercial use. More ⬇️

Today we’re releasing Code Llama, a large language model built on top of Llama 2, fine-tuned for coding & state-of-the-art for publicly available coding tools. Keeping with our open approach, Code Llama is publicly-available now for both research & commercial use. More ⬇️

AI at Meta

1,004,847 次观看 • 2 年前

It's wild what we're capable of with OCR now 🤯 Digitizing them unlocks the power of AI (and more!) for the insanely large corpus of Non-English PDFs Stay tuned for more :)

It's wild what we're capable of with OCR now 🤯 Digitizing them unlocks the power of AI (and more!) for the insanely large corpus of Non-English PDFs Stay tuned for more :)

Shahrukh Raza

10,706 次观看 • 1 年前

Moondream doesn’t just OCR, it understands. Full JSON receipts, instant Q&A. Open, tiny, blazingly fast.

Moondream doesn’t just OCR, it understands. Full JSON receipts, instant Q&A. Open, tiny, blazingly fast.

moondream

280,507 次观看 • 8 个月前

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Akshay 🚀

125,939 次观看 • 7 个月前

Vision Pro + on device AI 🤯🚀 We’re experimenting with more on device AI models, including LLaMa 3.2 3B. We might be adding this model to other platforms too. 😉

Vision Pro + on device AI 🤯🚀 We’re experimenting with more on device AI models, including LLaMa 3.2 3B. We might be adding this model to other platforms too. 😉

Craft.do

11,980 次观看 • 1 年前

Announcing Fireplexity v2 - our open source Perplexity-like example 🔥 Get instant AI answers with images and cited sources, powered by Firecrawl's new v2 endpoints and blazing fast @groqinc inference. Fork the repo and build your own AI answer app today 👇

Announcing Fireplexity v2 - our open source Perplexity-like example 🔥 Get instant AI answers with images and cited sources, powered by Firecrawl's new v2 endpoints and blazing fast @groqinc inference. Fork the repo and build your own AI answer app today 👇

Eric Ciarla (hiring)

39,002 次观看 • 9 个月前

I'm building a realtime video analysis app! It takes screenshots every 500ms, sends it to llama 4 on Together AI, and streams back the results. I want to extend it to be able to perform actions too (record my screen & send me a text when a video finishes for example). Will open source & launch it soon.

I'm building a realtime video analysis app! It takes screenshots every 500ms, sends it to llama 4 on Together AI, and streams back the results. I want to extend it to be able to perform actions too (record my screen & send me a text when a video finishes for example). Will open source & launch it soon.

Hassan

50,186 次观看 • 9 个月前