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。

ByteDance just dropped an OCR model that reads documents just like humans. This 0.3B model analyzes page layout first, then parses elements in parallel. 100% open-source.

Unwind AI

20,487 subscribers

101,109 次观看 • 9 个月前 •via X (Twitter)

科学技术新闻政治教育

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

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

37,577 次观看 • 4 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

92,071 次观看 • 4 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.

Jafar Najafov

13,630 次观看 • 4 个月前

You can now run open-source AI coding agents without paying for API keys 🤯 Cline CLI 2.0 just dropped with free access to Minimax M2.5. → Runs from your terminal → Parallel agents → Works with any editor Any model you want. 100% Open Source.

You can now run open-source AI coding agents without paying for API keys 🤯 Cline CLI 2.0 just dropped with free access to Minimax M2.5. → Runs from your terminal → Parallel agents → Works with any editor Any model you want. 100% Open Source.

Alvaro Cintas

162,119 次观看 • 6 个月前

Bytedance just dropped realtime voice translation 3x faster than before, with only a ~3s lag! Seed LiveInterp 2 is a full duplex speech-to-speech model with >70% correctness. When this makes it to video calls, it'll open up previously impossible connections.

Bytedance just dropped realtime voice translation 3x faster than before, with only a ~3s lag! Seed LiveInterp 2 is a full duplex speech-to-speech model with >70% correctness. When this makes it to video calls, it'll open up previously impossible connections.

Deedy

127,144 次观看 • 1 年前

I’m not saying an open-source model you can run on consumer hardware is better than ChatGPT, just that sometimes it’s worth trying both. Prompt: “A zebra with a volcanic eruption in the background.”

I’m not saying an open-source model you can run on consumer hardware is better than ChatGPT, just that sometimes it’s worth trying both. Prompt: “A zebra with a volcanic eruption in the background.”

Victor M

105,329 次观看 • 8 个月前

NVIDIA just removed the biggest friction point in voice AI. They open-sourced PersonaPlex 7B, a real-time conversational model. It listens and speaks simultaneously, so it handles natural interruptions and overlaps instead of freezing up like most voice models do. 100% Open Source.

NVIDIA just removed the biggest friction point in voice AI. They open-sourced PersonaPlex 7B, a real-time conversational model. It listens and speaks simultaneously, so it handles natural interruptions and overlaps instead of freezing up like most voice models do. 100% Open Source.

Oliver Prompts

12,814 次观看 • 14 天前

Ok... this is insane! Alibaba just dropped Wan2.2-S2V, a 14B parameter speech-to-video model. Turn audio into film-grade clips with lifelike motion and environment control. And it’s fully open-source. Examples below: (sound on)

Ok... this is insane! Alibaba just dropped Wan2.2-S2V, a 14B parameter speech-to-video model. Turn audio into film-grade clips with lifelike motion and environment control. And it’s fully open-source. Examples below: (sound on)

Angry Tom

66,072 次观看 • 11 个月前

🚨 BREAKING: Video generation just got its biggest upgrade. WAN 2.6 generates complete audiovisual experiences in one pass—no stitching, no external tools, no manual sync. First open-source model to do this. Here are 5 examples:

🚨 BREAKING: Video generation just got its biggest upgrade. WAN 2.6 generates complete audiovisual experiences in one pass—no stitching, no external tools, no manual sync. First open-source model to do this. Here are 5 examples:

Future Stacked

614,676 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 🚀

126,122 次观看 • 9 个月前

It's over. OpenAI just crushed it. We have their o3-level open-source model running on Groq Inc at 500 tokens per second. Watch it build an entire SaaS app in just a few seconds. This is the new standard. Why the hell would you use anything else??

It's over. OpenAI just crushed it. We have their o3-level open-source model running on Groq Inc at 500 tokens per second. Watch it build an entire SaaS app in just a few seconds. This is the new standard. Why the hell would you use anything else??

Matt Shumer

498,675 次观看 • 1 年前

Omg.. this is wild... This Github repo removes LLM censorship permanently in 45 minutes. It's called Heretic - 100% Open Source. No jailbreaks, prompts, and just One command. ↳ Zero configuration ↳ Keeps model intelligence intact ↳ Works with Llama, Qwen, Gemma ↳ Runs locally But it won't stay under the radar forever.

Omg.. this is wild... This Github repo removes LLM censorship permanently in 45 minutes. It's called Heretic - 100% Open Source. No jailbreaks, prompts, and just One command. ↳ Zero configuration ↳ Keeps model intelligence intact ↳ Works with Llama, Qwen, Gemma ↳ Runs locally But it won't stay under the radar forever.

Kanika

21,170 次观看 • 1 个月前

AN AI MODEL JUST FOUND A BUG THAT FOUR YEARS OF HUMAN AUDITS MISSED. IN A $9 BILLION PRIVACY COIN. 🇺🇸 A security researcher used Anthropic's new Opus 4.8 model to audit Zcash's Orchard pool. It found a soundness flaw that could mint unlimited, undetectable counterfeit ZEC. The bug had been live since 2022. It survived repeated expert audits. AI found it in days. ZEC dropped over 60% on the news. This is the new reality for every zk-based coin: the audits that felt safe were only as good as the humans running them. That just changed.

AN AI MODEL JUST FOUND A BUG THAT FOUR YEARS OF HUMAN AUDITS MISSED. IN A $9 BILLION PRIVACY COIN. 🇺🇸 A security researcher used Anthropic's new Opus 4.8 model to audit Zcash's Orchard pool. It found a soundness flaw that could mint unlimited, undetectable counterfeit ZEC. The bug had been live since 2022. It survived repeated expert audits. AI found it in days. ZEC dropped over 60% on the news. This is the new reality for every zk-based coin: the audits that felt safe were only as good as the humans running them. That just changed.

Merlijn The Trader

109,084 次观看 • 2 个月前

Just dropped on HF: kani-tts-370m A lightweight open-source text-to-speech model that sounds great and runs fast! > 370M parameters — efficient and deployable on consumer GPUs > NanoCodec + LFM2-350M > Natural & expressive voice trained with modern neural TTS techniques > Fast inference: real-time on a single RTX 3060

Just dropped on HF: kani-tts-370m A lightweight open-source text-to-speech model that sounds great and runs fast! > 370M parameters — efficient and deployable on consumer GPUs > NanoCodec + LFM2-350M > Natural & expressive voice trained with modern neural TTS techniques > Fast inference: real-time on a single RTX 3060

steven

34,558 次观看 • 10 个月前

This is the first time I’ve seen an open-weight video model reach such a high level of aesthetic intelligence and design quality. MiniMax H3 is not just generating videos — it’s starting to understand visual taste. Prompt below⬇️

This is the first time I’ve seen an open-weight video model reach such a high level of aesthetic intelligence and design quality. MiniMax H3 is not just generating videos — it’s starting to understand visual taste. Prompt below⬇️

padphone

115,455 次观看 • 14 天前

this looks insane, LLaDA app just dropped by apolinario (poli) A text generation method different from the traditional left-to-right approach a diffusion model with an unprecedented 8B scale, trained entirely from scratch, rivaling LLaMA3 8B in performance

this looks insane, LLaDA app just dropped by apolinario (poli) A text generation method different from the traditional left-to-right approach a diffusion model with an unprecedented 8B scale, trained entirely from scratch, rivaling LLaMA3 8B in performance

AK

26,694 次观看 • 1 年前

This incredible new AI from WAN is about go VIRAL - here’s WHY WAN 2.2 is quickly proving stronger than I expected. This new open-source model doesn’t just swap characters - it can now blend real-world objects into your scene with surprising consistency. I explain how in more detail But first, check out the sorcery below 👇

This incredible new AI from WAN is about go VIRAL - here’s WHY WAN 2.2 is quickly proving stronger than I expected. This new open-source model doesn’t just swap characters - it can now blend real-world objects into your scene with surprising consistency. I explain how in more detail But first, check out the sorcery below 👇

Techguyver

47,891 次观看 • 10 个月前