Generalizing an LLM from 8k to 1M Context using Qwen-Agent | Qwen
In this blog, we have introduced how to build the agent that is capable of handling 1M-context with a 8k-context model. It then becomes obvious how to synthesize the data once the agent is prepared. For instance, we could enlist volunteers to interact with the agents and record the outcomes to construct the fine-tuning dataset. […]
The Crash and Rebirth of a Six-Year-Old Open Source Project – DIYgod
The project was developed six years ago, and many trendy Node.js technologies and dependencies that were touted as the “Next Generation” at that time have become outdated. Many popular new technologies nowadays cannot be applied, such as JSX, TypeScript, Serverless, etc. Its architecture is also very unreasonable, with information about each route scattered in multiple […]
Anthropic’s Prompt Engineering Interactive Tutorial
Claude is sensitive to patterns (in its early years, before finetuning, it was a raw text-prediction tool), and it’s more likely to make mistakes when you make mistakes, smarter when you sound smart, sillier when you sound silly, and so on. Source: Anthropic’s Prompt Engineering Interactive Tutorial
Bytes Are All You Need: Transformers Operating Directly On File Bytes – Apple Machine Learning Research
our model requires absolutely no modality-specific processing at inference time, and uses an order of magnitude fewer parameters at equivalent accuracy on ImageNet. We demonstrate that the same ByteFormer architecture can perform audio classification without modifications or modality-specific preprocessing Source: Bytes Are All You Need: Transformers Operating Directly On File Bytes – Apple Machine Learning […]
Online Cryptography Course by Dan Boneh
Stanford course on computer cryptography. Source: Online Cryptography Course by Dan Boneh
Bringing developer choice to Copilot with Anthropic’s Claude 3.5 Sonnet, Google’s Gemini 1.5 Pro, and OpenAI’s o1-preview
It’s increasingly clear that any strategy that ties you to models from exclusively one provider is short-sighted. The best available model for a task can change every few months, and for something like AI code assistance model quality matters a lot. Getting stuck with a model that’s no longer best in class could be a […]
Carpentopod: A walking table project
some software for fun to generate various optimized walking mechanisms. And when I also picked up some electronics and wood working skills in more recent years, I was able to turn one of these mechanisms into an actual wireless walking wooden coffee table: the Carpentopod. Source: Carpentopod: A walking table project 木 牛流马
Brain waste-clearance system shown in people for first time | National Institutes of Health (NIH)
Though less well-known than the body’s blood vessels, the lymphatic system is also vital to health. The network of lymphatic vessels threaded throughout the body removes dead cells and other waste from the bloodstream. It also helps transport the immune cells that fight infections. It was once thought that the lymphatic system didn’t reach into […]
How to use VSCode/Cursor for iOS development | by Thomas Ricouard | Oct, 2024 | Medium
Source: How to use VSCode/Cursor for iOS development | by Thomas Ricouard | Oct, 2024 | Medium
How I Am Maintaining Multiple Emails For Git On A Same Machine – blag
direnv is one nifty tool which lets you have different environment variables based on directories/path. The best part is, as soon as you enter into a directory, direnv does it’s magic, so you don’t have to remember that you have to run direnv Source: How I Am Maintaining Multiple Emails For Git On A Same […]