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。

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... show more

Avi Chawla

70,413 subscribers

15,610 次观看 • 1 年前 •via X (Twitter)

健康养生教育科学技术

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 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!

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

443,826 次观看 • 1 年前

Today Meta released "Code Llama", a large language model fine-tuned for coding tasks. It's publicly available and can be used for commercial use! It outperforms GPT 3.5 and you can even run it locally on your Macbook using Ollama.

Today Meta released "Code Llama", a large language model fine-tuned for coding tasks. It's publicly available and can be used for commercial use! It outperforms GPT 3.5 and you can even run it locally on your Macbook using Ollama.

Marcel Pociot 🧪

50,094 次观看 • 2 年前

Meta just announced that Code Llama was now free for both research and commercial. This might the strongest competitor to ChatGPT: ▸ Can generate, explain, and debug your code ▸ Handles input 100,000 tokens ▸ Free for research + commercial use ▸ Outperforms most open models ▸ Comes in 7B, 13B, and 34B ▸ Supports Python, C++, Java, PHP, Typescript (Javascript), C#, and Bash Available in: ▸ Foundation base models (Code Llama) ▸ Python specializations (Code Llama - Python), ▸ Instruction-following models (Code Llama - Instruct)

Meta just announced that Code Llama was now free for both research and commercial. This might the strongest competitor to ChatGPT: ▸ Can generate, explain, and debug your code ▸ Handles input 100,000 tokens ▸ Free for research + commercial use ▸ Outperforms most open models ▸ Comes in 7B, 13B, and 34B ▸ Supports Python, C++, Java, PHP, Typescript (Javascript), C#, and Bash Available in: ▸ Foundation base models (Code Llama) ▸ Python specializations (Code Llama - Python), ▸ Instruction-following models (Code Llama - Instruct)

Lior Alexander

196,384 次观看 • 2 年前

Advent of Claude Day 31 - Claude Agent SDK I saved the best for last. The same agent loop, tools, and context management that power Claude Code is available as an SDK. Build agents that work like Claude Code in as little as 10 lines of code. This is just the beginning. 🎇🥂

Advent of Claude Day 31 - Claude Agent SDK I saved the best for last. The same agent loop, tools, and context management that power Claude Code is available as an SDK. Build agents that work like Claude Code in as little as 10 lines of code. This is just the beginning. 🎇🥂

Ado

100,117 次观看 • 6 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

Code LLaMA is now on Perplexity’s LLaMa Chat! Try asking it to write a function for you, or explain a code snippet: 🔗 This is the fastest way to try AI at Meta’s latest code-specialized LLM. With our model deployment expertise, we are able to provide you with this model less than 24 hours of it’s release. What’s next? We’ll integrate code LLaMA into Perplexity, all in service of providing you with the best answers to your most technical questions!

Code LLaMA is now on Perplexity’s LLaMa Chat! Try asking it to write a function for you, or explain a code snippet: 🔗 This is the fastest way to try AI at Meta’s latest code-specialized LLM. With our model deployment expertise, we are able to provide you with this model less than 24 hours of it’s release. What’s next? We’ll integrate code LLaMA into Perplexity, all in service of providing you with the best answers to your most technical questions!

Perplexity

274,561 次观看 • 2 年前

LM Studio 0.3.4 ships with Apple MLX 🚢🍎 Run on-device LLMs super fast, 100% locally and offline on your Apple Silicon Mac! Includes: > run Llama 3.2 1B at ~250 tok/sec (!) on M3 > enforce structured JSON responses > use via chat UI, or from your own code > run multiple models simultaneously > download any model from Hugging Face Video at 1x speed.

LM Studio 0.3.4 ships with Apple MLX 🚢🍎 Run on-device LLMs super fast, 100% locally and offline on your Apple Silicon Mac! Includes: > run Llama 3.2 1B at ~250 tok/sec (!) on M3 > enforce structured JSON responses > use via chat UI, or from your own code > run multiple models simultaneously > download any model from Hugging Face Video at 1x speed.

LM Studio

171,770 次观看 • 1 年前

Chat GPT inside VS Code! Find bugs, add comments, explain code and more! (how to do it yourself in the next tweet)

Chat GPT inside VS Code! Find bugs, add comments, explain code and more! (how to do it yourself in the next tweet)

Jarrod Watts

269,814 次观看 • 3 年前

Introducing Dexter. An open source financial agent in ~200 lines of code. Think: Claude Code, but for finance. What Dexter does today: • plans tasks • runs on its own • validates its work • researches stocks It’s built with OSS tools like for managing LLMs, prompts, outputs, etc. No coding experience needed to run. Goal: build the best financial agent and share every line of code along the way. Next: evals, starting with

Introducing Dexter. An open source financial agent in ~200 lines of code. Think: Claude Code, but for finance. What Dexter does today: • plans tasks • runs on its own • validates its work • researches stocks It’s built with OSS tools like for managing LLMs, prompts, outputs, etc. No coding experience needed to run. Goal: build the best financial agent and share every line of code along the way. Next: evals, starting with

Virat Singh

317,057 次观看 • 8 个月前

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

1,004,879 次观看 • 2 年前

I just customized the scrollbar on my latest Framer project using Chat GPT. It took me 3 minutes and I know less about code than a drywall. Totally transformed the feel of my site. Here's a step-by-step of how I did it 👇🏼

I just customized the scrollbar on my latest Framer project using Chat GPT. It took me 3 minutes and I know less about code than a drywall. Totally transformed the feel of my site. Here's a step-by-step of how I did it 👇🏼

Erman Malak

31,306 次观看 • 3 年前

My previous tweet received 120+ retweets, so I recreated the zoom effect from in Framer without using any code. No-code demo: 🎁 If this post gets 1K+ likes, I'll share the remix link for free.

My previous tweet received 120+ retweets, so I recreated the zoom effect from in Framer without using any code. No-code demo: 🎁 If this post gets 1K+ likes, I'll share the remix link for free.

Framer University

38,553 次观看 • 3 年前

Here's the Rive source file and the code behind it. The Rive file is available on the Rive Rive Marketplace, and I'll also share the code below. Apologies in advance for the messy file structure and naming conventions. At some point I stopped naming things properly and chose chaos instead.

Here's the Rive source file and the code behind it. The Rive file is available on the Rive Rive Marketplace, and I'll also share the code below. Apologies in advance for the messy file structure and naming conventions. At some point I stopped naming things properly and chose chaos instead.

Angga Motion

54,618 次观看 • 14 天前

it's day 6 of sharing code + tutorials for my computer vision projects "fun with computer vision dot com" 🪬 thank you to everyone for the incredible support on my launch we're up to 126 customers now next steps: > "Floor is Lava" code + tutorial will be released this week > making more video content and cross-sharing on yt / tt / ig (thank you jack friks for the inspiration to post widely and post often) > creating more structure and engagement in our discord server

it's day 6 of sharing code + tutorials for my computer vision projects "fun with computer vision dot com" 🪬 thank you to everyone for the incredible support on my launch we're up to 126 customers now next steps: > "Floor is Lava" code + tutorial will be released this week > making more video content and cross-sharing on yt / tt / ig (thank you jack friks for the inspiration to post widely and post often) > creating more structure and engagement in our discord server

AA

179,523 次观看 • 1 年前

here's how the whole thing works. claude code doesn't care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.

here's how the whole thing works. claude code doesn't care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.

Sudo su

37,580 次观看 • 4 个月前

I started building an AI Financial Agent. Today, I am launching the production app. My goal is to let: • developers see the code as I build • non-developers use the app as I build All of the code is open source. It'll combine LangChain and Vercel AI SDK. Right now, the agent can access stock prices. I am adding fundamentals data next. Let me know what features you want to see.

I started building an AI Financial Agent. Today, I am launching the production app. My goal is to let: • developers see the code as I build • non-developers use the app as I build All of the code is open source. It'll combine LangChain and Vercel AI SDK. Right now, the agent can access stock prices. I am adding fundamentals data next. Let me know what features you want to see.

virat

75,792 次观看 • 1 年前

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 🚀

126,077 次观看 • 7 个月前

Update: it’s even easier and faster now. If the PNL card has a referral code, you can just save it and upload it to Hyperview. It will detect the referral code and automatically redirect you to the wallet. If there’s no referral code it will automatically extract the entry price, leverage and trade direction to find matching positions like in the video below.

Update: it’s even easier and faster now. If the PNL card has a referral code, you can just save it and upload it to Hyperview. It will detect the referral code and automatically redirect you to the wallet. If there’s no referral code it will automatically extract the entry price, leverage and trade direction to find matching positions like in the video below.

Alex

26,930 次观看 • 2 个月前

🚀 [New Project] Personal Website (HTML, CSS, JavaScript) I built this Personal Website Template and sharing the code for FREE! I am sharing what I build every week and creating awesome web components. For the source code: 👉 Follow Me 👉 Like 👉 Retweet 👉 Comment "Code"

🚀 [New Project] Personal Website (HTML, CSS, JavaScript) I built this Personal Website Template and sharing the code for FREE! I am sharing what I build every week and creating awesome web components. For the source code: 👉 Follow Me 👉 Like 👉 Retweet 👉 Comment "Code"

Tan Gravam

168,702 次观看 • 3 年前

Sidekick has 20+ new capabilities in this Edition. My favorite: it can create custom apps. Just prompt Sidekick, and it writes the app code using Polaris UI with Admin API GraphQL queries and mutations.

Sidekick has 20+ new capabilities in this Edition. My favorite: it can create custom apps. Just prompt Sidekick, and it writes the app code using Polaris UI with Admin API GraphQL queries and mutations.

tobi lutke

17,392 次观看 • 6 个月前