open-source
![Brian Piercy](data:image/svg+xml;utf8,<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="%230A66C2"><path d="M20.447 20.452H16.89v-5.569c0-1.328-.027-3.037-1.852-3.037-1.853 0-2.136 1.445-2.136 2.939v5.667H9.351V9h3.414v1.561h.046c.477-.9 1.637-1.85 3.37-1.85 3.601 0 4.267 2.37 4.267 5.455v6.286zM5.337 7.433a1.982 1.982 0 1 1 0-3.964 1.982 1.982 0 0 1 0 3.964zm1.782 13.019H3.555V9h3.564v11.452zM22.225 0H1.771C.792 0 0 .774 0 1.729v20.542C0 23.227.792 24 1.771 24h20.451C23.2 24 24 23.227 24 22.271V1.729C24 .774 23.2 0 22.222 0h.003z"/></svg>)
Chinese AI lab Z.ai released GLM-5.2 to their coding plan subscribers on June 13th, and then yesterday (June 16th) released the full open weights under an MIT license. Similar in …
Library of open source PDKs
In this article, I’ll go over the open-source LLMs you should know and when to use them. All Open-Source LLMs to know.
Looking for a 3D printer brand more welcoming to owners' tinkering after the Bambu Labs uproar? Let me introduce the Czech Republic's Prusa.
The open-source 3D printing community is lining up to fund a war against Bambu Lab, after it threatened a developer who modified its open-source code.
6 Open-Source Libraries to FineTune LLMs 1. Unsloth GitHub: https://lnkd.in/gQvPWVFb → Fastest way to fine-tune LLMs locally → Optimized for low VRAM (even laptops) → Plug-and-play with Hugging Face models 2. Axolotl GitHub: https://lnkd.in/g34kuExT → Flexible LLM fine-tuning configs → Supports LoRA, QLoRA, multi-GPU → Great for custom training pipelines 3. TRL (Transformer Reinforcement Learning) GitHub: https://lnkd.in/gnxQBVAc → RLHF, DPO, PPO for LLM alignment → Built on Hugging Face ecosystem → Essential for post-training optimization 4. DeepSpeed GitHub: https://lnkd.in/gEdkFWdB → Train massive models efficiently → Memory + speed optimization → Industry standard for scaling 5. LLaMA-Factory GitHub: https://lnkd.in/gbdWBDsD → All-in-one fine-tuning UI + CLI → Supports multiple models (LLaMA, Qwen, etc.) → Beginner-friendly + powerful 6. PEFT GitHub: https://lnkd.in/g7fBjh2E → Fine-tune with minimal compute → LoRA, adapters, prefix tuning → Best for cost-efficient training Save this for future use. | 46 comments on LinkedIn
Software engineers are, if not unique, then darn near unique in the ease with which we can create tools to improve our own professional lives; this however can …
Whether it is a 0.8B model running on a smartphone or a 9B model powering a coding terminal, the Qwen3.5 series is effectively democratizing the "agentic era."
Motorola has announced a partnership with GrapheneOS which will see a phone with support, as well as features ported to other devices.
The largest collection of free stuff on the internet!
A list of open source games
FPGAs are limited by outdated proprietary software. Learn how embracing open-source tools is necessary to modernize FPGA development and unlock their full potential.
New research reveals open-source AI models use up to 10 times more computing resources than closed alternatives, potentially negating cost advantages for enterprise deployments.
The crawl archive for May 2024 is now available. The data was crawled between May 18th and May 31st, and contains 2.7 billion web pages (or 377 TiB of uncompressed content). This is our 100th crawl!
if the centralizing forces of data and compute hold, open and closed-source AI cannot both dominate long-term
Just like our roads, bridges, electrical grid and airports will deteriorate without public investment, so will our software infrastructure without action.
What is OpenTofu OpenTofu is an open-source Terraform fork, a drop-in replacement for...
Artificial intelligence (AI) has become an integral part of our daily lives and these best AI freeware of 2024 are
In a previous post, I demonstrated how to implement RAG using the Load-Transform-Embed-Store...
The top open source Large Language Models available for commercial use are as follows. Llama - 2 Meta released Llama 2, a set of pretrained and refined LLMs, along with Llama 2-Chat, a version of Llama 2. These models are scalable up to 70 billion parameters. It was discovered after extensive testing on safety and helpfulness-focused benchmarks that Llama 2-Chat models perform better than current open-source models in most cases. Human evaluations have shown that they align well with several closed-source models. The researchers have even taken a few steps to guarantee the security of these models. This includes annotating
Magma is an open-source software platform that gives network operators an open, flexible and extensible mobile core network solution.
Open-source software is one of the most influential initiatives ever made in the history of computer science and programming. The phrase “open source” means something that’s open for people to use…
After more than 12.000 Github stars, two successful open-source projects, a failed open-core company, and a successful prop-tech one*, I feel more than ever that giving your product away for free is just as bad a business strategy as it sounds.
Automated updates and community-driven tools like OpenRewrite help developers tackle dependency challenges and streamline software maintenance.