Загрузка видео...

Не удалось загрузить видео

На главную

Announcing jina-ocr-v1, our new visual document parser with 3.4B total parameters and 570M active parameters, with speculative decoding built in. Throw PDFs, scans, tables, charts, or invoices at it and get clean markdown back. Available on 🤗 & Jina Reader `x-respond-with` today

JinaAI_'s profile picture

Jina AI

17,851 subscribers

154,660 просмотров • 3 дней назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

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!
0:13

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

443,929 просмотров • 1 год назад

We're launching 5x faster document parsing in the Firecrawl MCP. Use /parse to turn PDFs, spreadsheets, and docs into LLM-ready data for your agents. Supports running locally or with our hosted MCP server. Try it out today with no API key required on our free tier!
0:18

We're launching 5x faster document parsing in the Firecrawl MCP. Use /parse to turn PDFs, spreadsheets, and docs into LLM-ready data for your agents. Supports running locally or with our hosted MCP server. Try it out today with no API key required on our free tier!

Firecrawl

47,432 просмотров • 2 месяцев назад

Baidu just open-sourced an OCR model that reads entire 40-page documents in one shot. It's called Unlimited-OCR. 3 billion parameters but only 500 million active during inference. Runs 100% locally on your machine. Why this matters: traditional OCR tools chop documents page by page. Tables that span two pages break. Reading order gets lost. Cross-page context disappears. Unlimited-OCR processes the whole document at once. 32K context window. Text, formulas, tables, reading order all preserved across pages. Output comes out as clean structured Markdown. → 93% accuracy on the standard benchmark. +6 points over the baseline. → Error rate stays below 0.11 even past 40 pages. → Multilingual out of the box. → 2.12 million downloads on Hugging Face last month. 14,600 GitHub stars. For context: Amazon Textract, Google Cloud Vision, and Azure Document Intelligence all charge per page. This runs locally for free.
0:13

Baidu just open-sourced an OCR model that reads entire 40-page documents in one shot. It's called Unlimited-OCR. 3 billion parameters but only 500 million active during inference. Runs 100% locally on your machine. Why this matters: traditional OCR tools chop documents page by page. Tables that span two pages break. Reading order gets lost. Cross-page context disappears. Unlimited-OCR processes the whole document at once. 32K context window. Text, formulas, tables, reading order all preserved across pages. Output comes out as clean structured Markdown. → 93% accuracy on the standard benchmark. +6 points over the baseline. → Error rate stays below 0.11 even past 40 pages. → Multilingual out of the box. → 2.12 million downloads on Hugging Face last month. 14,600 GitHub stars. For context: Amazon Textract, Google Cloud Vision, and Azure Document Intelligence all charge per page. This runs locally for free.

Vaibhav Sisinty

415,916 просмотров • 2 месяцев назад

🔥 GLM-5.3-Flash Hits #1 on 🐮 GLM-5.3-Flash (Ox Alpha) is now the most-used and most popular model on with cumulative token throughput surpassing 2.41 trillion tokens. As the first native omni-modal model in the GLM-5 series, it packs 320B total parameters, with 18B active, and features a hybrid sparse and linear attention architecture with a 1M-token context window. The result: lightning-fast responses, powerful reasoning, and outstanding cost efficiency. 🎁 Still 100% FREE on From high-frequency API calls and coding to complex Agents and long-document processing, jump in and experience the #1 model on for yourself! 👉 Try it free now:
0:13

🔥 GLM-5.3-Flash Hits #1 on 🐮 GLM-5.3-Flash (Ox Alpha) is now the most-used and most popular model on with cumulative token throughput surpassing 2.41 trillion tokens. As the first native omni-modal model in the GLM-5 series, it packs 320B total parameters, with 18B active, and features a hybrid sparse and linear attention architecture with a 1M-token context window. The result: lightning-fast responses, powerful reasoning, and outstanding cost efficiency. 🎁 Still 100% FREE on From high-frequency API calls and coding to complex Agents and long-document processing, jump in and experience the #1 model on for yourself! 👉 Try it free now:

B.AI

220,039 просмотров • 16 дней назад

Parsing PDFs at scale with LLMs is cost prohibitive. Newer models (e.g. gemini 3) are good at reading pdfs, but you burn unnecessary vision tokens even when the page is text heavy. We’ve built in a “cost-optimizer” within LlamaParse that will dynamically route pages to fast/cheap parsing depending on its complexity. Complex pages (e.g. those with tables/charts/diagrams) will still get routed to our VLM-enabled modes. This will let you save anywhere from 50-90% of parsing costs, at much higher accuracy compared to the comparable mode of feeding screenshots into VLMs. Check it out!
0:17

Parsing PDFs at scale with LLMs is cost prohibitive. Newer models (e.g. gemini 3) are good at reading pdfs, but you burn unnecessary vision tokens even when the page is text heavy. We’ve built in a “cost-optimizer” within LlamaParse that will dynamically route pages to fast/cheap parsing depending on its complexity. Complex pages (e.g. those with tables/charts/diagrams) will still get routed to our VLM-enabled modes. This will let you save anywhere from 50-90% of parsing costs, at much higher accuracy compared to the comparable mode of feeding screenshots into VLMs. Check it out!

Jerry Liu

55,848 просмотров • 7 месяцев назад

With Paul and the crew back on the road today, it’s time to get geared up. Here’s a sneak peek of the new merch celebrating all of Paul’s musical eras. For those not going on tour, it will be available on our store.
0:20

With Paul and the crew back on the road today, it’s time to get geared up. Here’s a sneak peek of the new merch celebrating all of Paul’s musical eras. For those not going on tour, it will be available on our store.

Paul Weller

16,552 просмотров • 3 месяцев назад

Complex workflow? Break it down into sub-workflows for better performance and easier re-use. Now, it’s too easy not to. Steps to get more modular workflows: 1. Select a set of connected nodes 2. Right-click and select Convert to sub-workflow (or Alt + X) 3. Watch magic happen 🪄 🎩 This action will opened a new tab and paste in the selected nodes with their parameters intact! For the encore, the selected nodes in the original workflow will be replaced automagically with a Call My Sub-workflow node. #n8n #lowcode #awesome
0:16

Complex workflow? Break it down into sub-workflows for better performance and easier re-use. Now, it’s too easy not to. Steps to get more modular workflows: 1. Select a set of connected nodes 2. Right-click and select Convert to sub-workflow (or Alt + X) 3. Watch magic happen 🪄 🎩 This action will opened a new tab and paste in the selected nodes with their parameters intact! For the encore, the selected nodes in the original workflow will be replaced automagically with a Call My Sub-workflow node. #n8n #lowcode #awesome

n8n.io

71,328 просмотров • 1 год назад

SEGA x THEM Skates – TURBO now shipping. Celebrating Jet Set Radio’s 25th anniversary, this limited‑edition skate pays tribute to the game’s iconic cel‑shaded style with vibrant neon accents and original early‑2000s artwork. Built on THEM’s trusted 909 boot, it delivers smooth, street‑ready performance and is available in 80mm or 58mm setups. Available at and select skate shops worldwide.
0:11

SEGA x THEM Skates – TURBO now shipping. Celebrating Jet Set Radio’s 25th anniversary, this limited‑edition skate pays tribute to the game’s iconic cel‑shaded style with vibrant neon accents and original early‑2000s artwork. Built on THEM’s trusted 909 boot, it delivers smooth, street‑ready performance and is available in 80mm or 58mm setups. Available at and select skate shops worldwide.

SEGA

195,216 просмотров • 5 месяцев назад

🎉 A Special Announcement from the $GAYU Family. Today, we celebrate a milestone beyond the charts. Our developer GAYU_BTC has officially married the love of his life a moment of genuine joy for our entire community. Congratulations on this beautiful new chapter. 🥂 Behind every strong project is a team building with purpose, and today reminds us that $GAYU is powered by real people with real lives, real milestones, and real dedication. To our community, this week brings a lot of momentum stay active, stay engaged, and stay ready. There's plenty happening behind the scenes, and we're excited to share it with you soon. Congratulations once again. Here's to new beginnings in life, and in $GAYU DYOR CA: 5pDbcXKVk9FMCz7P31iaezva7iR3rGWhJz6TQU6Qpump
0:19

🎉 A Special Announcement from the $GAYU Family. Today, we celebrate a milestone beyond the charts. Our developer GAYU_BTC has officially married the love of his life a moment of genuine joy for our entire community. Congratulations on this beautiful new chapter. 🥂 Behind every strong project is a team building with purpose, and today reminds us that $GAYU is powered by real people with real lives, real milestones, and real dedication. To our community, this week brings a lot of momentum stay active, stay engaged, and stay ready. There's plenty happening behind the scenes, and we're excited to share it with you soon. Congratulations once again. Here's to new beginnings in life, and in $GAYU DYOR CA: 5pDbcXKVk9FMCz7P31iaezva7iR3rGWhJz6TQU6Qpump

GAYU

10,593 просмотров • 1 месяц назад

Hey Smith & Wesson Inc., I got a new Shield X. It’s got a false reset, so I sent it in to get fixed. Just got it back and was told nothing is wrong with it. Am I crazy or is making consistent follow-up shots impossible a new “feature” on your flagship CCW?
0:10

Hey Smith & Wesson Inc., I got a new Shield X. It’s got a false reset, so I sent it in to get fixed. Just got it back and was told nothing is wrong with it. Am I crazy or is making consistent follow-up shots impossible a new “feature” on your flagship CCW?

The Fat Electrician

337,668 просмотров • 8 месяцев назад

~ Introducing Oracler 🧿~ Navigating the crypto space and staying ahead of the curve isn’t easy. That’s why we built ultimate AI-powered platform to transform how crypto is traded. With lightning-fast analytics and seamless mobile auto-trading at your fingertips, get ready for an edge in this fast-moving world of crypto. 💡 Real-Time Token Insights live insights into new coin performances, trends, and key narratives driving the market at that instance. 🧠 Mindshare Analytics Monitor your favourite influencers. No more endless scrolling or guessing—know what’s trending and take action instantly. 🐵 Auto-Trading Made Simple Customize your parameters and let Oracler handle the rest. Execute trades with one click—available on both desktop and mobile. You're early. Grab your access code. ◻️◻️◻️◻️◻️◻️
0:16

~ Introducing Oracler 🧿~ Navigating the crypto space and staying ahead of the curve isn’t easy. That’s why we built ultimate AI-powered platform to transform how crypto is traded. With lightning-fast analytics and seamless mobile auto-trading at your fingertips, get ready for an edge in this fast-moving world of crypto. 💡 Real-Time Token Insights live insights into new coin performances, trends, and key narratives driving the market at that instance. 🧠 Mindshare Analytics Monitor your favourite influencers. No more endless scrolling or guessing—know what’s trending and take action instantly. 🐵 Auto-Trading Made Simple Customize your parameters and let Oracler handle the rest. Execute trades with one click—available on both desktop and mobile. You're early. Grab your access code. ◻️◻️◻️◻️◻️◻️

Oracler X 🧙‍♂️

144,429 просмотров • 1 год назад

After months of work, and with the help of our awesome community, we're excited to finally share LM Studio 0.3.0! 🎉 🔥 What's new: - Built-in Chat with Documents, 100% offline - OpenAI-like 'Structured Outputs' API with any local model - Total UI revamp (with dark/light/sepia themes) - Load & serve multiple LLMs *on the local network* - Available in 7 languages! 🌎🌍🌏 - Download any supported model from Hugging Face - Update LLM runtimes (llama.cpp) separately from the app ... and tons more goodies! Let us know how you like it! 👾🤝
0:19

After months of work, and with the help of our awesome community, we're excited to finally share LM Studio 0.3.0! 🎉 🔥 What's new: - Built-in Chat with Documents, 100% offline - OpenAI-like 'Structured Outputs' API with any local model - Total UI revamp (with dark/light/sepia themes) - Load & serve multiple LLMs *on the local network* - Available in 7 languages! 🌎🌍🌏 - Download any supported model from Hugging Face - Update LLM runtimes (llama.cpp) separately from the app ... and tons more goodies! Let us know how you like it! 👾🤝

LM Studio

142,641 просмотров • 2 лет назад

If you need McKinsey-style slides, try this prompt: I asked Kimi to conduct a comprehensive analysis of the GenAI video model market, focusing on leading players (e.g., Seedance 2.0, Sora, Kling, Veo, Luma). My prompt: Conduct a comprehensive analysis of the GenAI video model market, focusing on leading players (e.g., Seedance 2.0, Kling, Veo, Luma). Compare their core architectures, temporal consistency, and prompt adherence to identify current industry benchmarks. Use the latest information Requirement: A professional, high-density consulting presentation slide, designed in the style of a top-tier strategy firm (McKinsey/BCG) blended with high-end editorial aesthetics. Core Content & Layout: 1. Rich Data Visualization: The slide is populated with complex, precise charts (stacked bar charts, waterfall charts, or line graphs) and detailed data tables with rows and columns. 2. Structured Frameworks: Includes strategic diagrams or 2x2 matrices constructed with thin, clean lines. 3. High Information Density: The layout is sophisticated and multi-column, mimicking an actual business analysis deck, not just an empty cover page. Visual Style: 1. Aesthetic: Tech-minimalist but information-heavy. Clean, sharp, and authoritative. 2. Typography: Serif fonts (like Times New Roman) for the main headlines to give a premium financial report feel; clean Sans-serif for chart labels and data numbers. 3. Color Palette: Clean white background. Text is sharp black. Charts and graphical accents use Deep Royal Blue and distinct shades of grey for data hierarchy. 4. Graphics: Use fine hairline borders for tables and precise vector lines for graphs.
0:13

If you need McKinsey-style slides, try this prompt: I asked Kimi to conduct a comprehensive analysis of the GenAI video model market, focusing on leading players (e.g., Seedance 2.0, Sora, Kling, Veo, Luma). My prompt: Conduct a comprehensive analysis of the GenAI video model market, focusing on leading players (e.g., Seedance 2.0, Kling, Veo, Luma). Compare their core architectures, temporal consistency, and prompt adherence to identify current industry benchmarks. Use the latest information Requirement: A professional, high-density consulting presentation slide, designed in the style of a top-tier strategy firm (McKinsey/BCG) blended with high-end editorial aesthetics. Core Content & Layout: 1. Rich Data Visualization: The slide is populated with complex, precise charts (stacked bar charts, waterfall charts, or line graphs) and detailed data tables with rows and columns. 2. Structured Frameworks: Includes strategic diagrams or 2x2 matrices constructed with thin, clean lines. 3. High Information Density: The layout is sophisticated and multi-column, mimicking an actual business analysis deck, not just an empty cover page. Visual Style: 1. Aesthetic: Tech-minimalist but information-heavy. Clean, sharp, and authoritative. 2. Typography: Serif fonts (like Times New Roman) for the main headlines to give a premium financial report feel; clean Sans-serif for chart labels and data numbers. 3. Color Palette: Clean white background. Text is sharp black. Charts and graphical accents use Deep Royal Blue and distinct shades of grey for data hierarchy. 4. Graphics: Use fine hairline borders for tables and precise vector lines for graphs.

Crystal

707,951 просмотров • 7 месяцев назад

Since launching our free advanced desktop platform, Robinhood Legend, we’ve been busy making it even…. Better. We’ve heard you, and you know we love to build. Improvements: 1. Anchored VWAP: Analyze trends with precision by anchoring the Volume Weighted Average Price (VWAP) to key events or timeframes. A must-have for technical traders. 2. Chart comparisons: Compare multiple stocks, ETFs, or crypto assets on a single chart to spot trends and correlations with ease. 3. New columns on the options chain: Get deeper insights into your options trades with new probability metrics available directly on the options chain. See the options disclosure document at 4. New IV data: View implied volatility (IV) across more surfaces, including the options chain, watchlist, and positions table, for better-informed options trading. 5. Options replace: Modify working options orders instantly—no need to cancel and start over. 6. Joint accounts: Available to all customers on Robinhood Legend. Switch between account types and share trades with your partner in real-time. 7. Snapshot widget: Get key data on stocks, ETFs, indexes, and crypto—all in one place: Live quotes and price ranges, Recent headlines, Implied & historical volatility, Fundamentals and more. 8. Much more. Dive in and see for yourself.
0:11

Since launching our free advanced desktop platform, Robinhood Legend, we’ve been busy making it even…. Better. We’ve heard you, and you know we love to build. Improvements: 1. Anchored VWAP: Analyze trends with precision by anchoring the Volume Weighted Average Price (VWAP) to key events or timeframes. A must-have for technical traders. 2. Chart comparisons: Compare multiple stocks, ETFs, or crypto assets on a single chart to spot trends and correlations with ease. 3. New columns on the options chain: Get deeper insights into your options trades with new probability metrics available directly on the options chain. See the options disclosure document at 4. New IV data: View implied volatility (IV) across more surfaces, including the options chain, watchlist, and positions table, for better-informed options trading. 5. Options replace: Modify working options orders instantly—no need to cancel and start over. 6. Joint accounts: Available to all customers on Robinhood Legend. Switch between account types and share trades with your partner in real-time. 7. Snapshot widget: Get key data on stocks, ETFs, indexes, and crypto—all in one place: Live quotes and price ranges, Recent headlines, Implied & historical volatility, Fundamentals and more. 8. Much more. Dive in and see for yourself.

Robinhood

24,543 просмотров • 1 год назад

Inkling-small is out today! With SGLang, you can get 648 tok/s decode with DSpark (simulated acc len=4) and 288 tok/s w/o DSpark, under the same setup (8x NVIDIA AI B200, TP 8, NVFP4, bs=1). What makes this model different is the size. 276B total with 12B active is a sweet spot for RL, and both LoRA and full-parameter training become well within reach. Miles is ready and verified for multimodal RL on Inkling-small, so you can turn your multimodal data into real capability gains. At ~1/4 the size, Inkling-small matches the bigger version in capability and even wins on some benchmarks. Run Inkling-small with SGLang, and customize it with Miles.
0:18

Inkling-small is out today! With SGLang, you can get 648 tok/s decode with DSpark (simulated acc len=4) and 288 tok/s w/o DSpark, under the same setup (8x NVIDIA AI B200, TP 8, NVFP4, bs=1). What makes this model different is the size. 276B total with 12B active is a sweet spot for RL, and both LoRA and full-parameter training become well within reach. Miles is ready and verified for multimodal RL on Inkling-small, so you can turn your multimodal data into real capability gains. At ~1/4 the size, Inkling-small matches the bigger version in capability and even wins on some benchmarks. Run Inkling-small with SGLang, and customize it with Miles.

LMSYS Org

120,134 просмотров • 1 месяц назад

I am delighted to announce our partnership with Geco.one ! Starting today, DragonX tokens will be available as collateral for leverage trading with our new partner. Geco One ( Is an established, fully regulated European exchange with over 60,000 registered users. Today marks a first step in our partnership. I am excited to continue to work with their team to push Geco One and DragonX forward in adopting new ecosystems. As part of this partnership, the Geco One team was generous enough to facilitate a BitGo listing for DragonX. This is a big step forward, it opens up new opportunities for DragonX to be listed and partner with other regulated institutions. Give a shot today, you can use BTC/ETH/XRP/GECO/DRAGONX as collateral on leverage, going as much as 100x long or short. Geco One supports dozens of the most popular pairs. check them out today.
0:12

I am delighted to announce our partnership with Geco.one ! Starting today, DragonX tokens will be available as collateral for leverage trading with our new partner. Geco One ( Is an established, fully regulated European exchange with over 60,000 registered users. Today marks a first step in our partnership. I am excited to continue to work with their team to push Geco One and DragonX forward in adopting new ecosystems. As part of this partnership, the Geco One team was generous enough to facilitate a BitGo listing for DragonX. This is a big step forward, it opens up new opportunities for DragonX to be listed and partner with other regulated institutions. Give a shot today, you can use BTC/ETH/XRP/GECO/DRAGONX as collateral on leverage, going as much as 100x long or short. Geco One supports dozens of the most popular pairs. check them out today.

Erik

12,097 просмотров • 1 год назад

The human brain is truly a marvel of nature. If you horribly reductive, and boiled it down to a language model, you'd be looking at roughly 100 trillon parameters running as a sparse MoE architecture Only about 1-5% of neurons fire at any given moment, meaning the brain "activates" maybe 1-5 trillion parameters per inference step. For context, the largest AI models we've built probably top out around 5 trillion parameters. The brain is roughly 100x larger. Even its active params at any given moment are larger than almost every model in existence today. Here's what melts my brain (pun intnended) though Your brain does all of this on about 20 watts of power, less than a dim light bulb. Training a frontier AI model consumes enough electricity to power small cities for months. Running inference across data centers pulls megawatts. Your brain runs 24/7 for 80+ years on the equivalent of a phone charger. We haven't come close to matching the brain's scale. And we're not even in the same universe when it comes to efficiency. Evolution spent 500 million yrs optimizing the most energy-efficient intelligence architecture ever known. we're trying to brute force our way there with compute and electricity. Nature is still the best engineer in the room.
0:12

The human brain is truly a marvel of nature. If you horribly reductive, and boiled it down to a language model, you'd be looking at roughly 100 trillon parameters running as a sparse MoE architecture Only about 1-5% of neurons fire at any given moment, meaning the brain "activates" maybe 1-5 trillion parameters per inference step. For context, the largest AI models we've built probably top out around 5 trillion parameters. The brain is roughly 100x larger. Even its active params at any given moment are larger than almost every model in existence today. Here's what melts my brain (pun intnended) though Your brain does all of this on about 20 watts of power, less than a dim light bulb. Training a frontier AI model consumes enough electricity to power small cities for months. Running inference across data centers pulls megawatts. Your brain runs 24/7 for 80+ years on the equivalent of a phone charger. We haven't come close to matching the brain's scale. And we're not even in the same universe when it comes to efficiency. Evolution spent 500 million yrs optimizing the most energy-efficient intelligence architecture ever known. we're trying to brute force our way there with compute and electricity. Nature is still the best engineer in the room.

am.will

130,883 просмотров • 5 месяцев назад

Introducing Extend UI — open-source components for document agents - 14 components & examples for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more - fully customizable - MIT licensed when we started, we tried every file viewer and document component library we could find unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for Extend it was only ever meant to be internal, but enough customers kept asking for it that we decided to give it back to the community it's useful for building agents, user-facing document flows, or internal tools we use and maintain it for Extend ourselves, so it'll keep getting better over time (and it's battle tested on millions of pages running through our system every day) it also works with design system agents like Magic Patterns for faster exploration and prototyping available today on the shadcn component registry! some examples in 🧵
0:12

Introducing Extend UI — open-source components for document agents - 14 components & examples for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more - fully customizable - MIT licensed when we started, we tried every file viewer and document component library we could find unfortunately, none of them had all the functionality (and polish) that we wanted, so we ended up building our own for Extend it was only ever meant to be internal, but enough customers kept asking for it that we decided to give it back to the community it's useful for building agents, user-facing document flows, or internal tools we use and maintain it for Extend ourselves, so it'll keep getting better over time (and it's battle tested on millions of pages running through our system every day) it also works with design system agents like Magic Patterns for faster exploration and prototyping available today on the shadcn component registry! some examples in 🧵

Kushal Byatnal

171,158 просмотров • 3 месяцев назад

A simple solution to keep our streets clean ♻️ Instead of bottles and cans ending up in the wrong place, you now can leave them on these new bin surrounds, making it easy anyone to pick them up, recycle, and get the deposit back. I’ve seen these bin surrounds working well across Europe so pitched the idea to Dublin City Council and worked closely with the North Inner City task force and council officials to make it happen. Let's get these in Dún Laoghaire next!
0:19

A simple solution to keep our streets clean ♻️ Instead of bottles and cans ending up in the wrong place, you now can leave them on these new bin surrounds, making it easy anyone to pick them up, recycle, and get the deposit back. I’ve seen these bin surrounds working well across Europe so pitched the idea to Dublin City Council and worked closely with the North Inner City task force and council officials to make it happen. Let's get these in Dún Laoghaire next!

Ossian Smyth

254,049 просмотров • 1 год назад