InTowards AIbyArijit Sengupta·Nov 1How to Fine-Tune Qwen2.5 with LoRA and Publish Your Model on Hugging Face: A Step-by-Step GuideBuilding a fashion attribute extractor with teacher-generated data, a 0.5B student model, and Google Colab.
Shridhar Pawar·Oct 24Fine-tuning a 0.5B code model with LoRA on a free Colab GPUA 494-million-parameter coding model, 8,000 Python examples, one free T4 GPU and 16 minutes of training: here is exactly how it works, what…
SDNTechForum·Oct 12No GPU Required: How to Run a Private LLM API on a Budget Linux MachineYou don’t need a multi-thousand-dollar workstation or an enterprise GPU cluster to run your own AI. With the right combination of open…
InTowards AIbyMayurnayak·Sep 18GRPO for Safety Post-Training: An Experiment with Qwen2.5–0.5BOverview:A response icon2A response icon2
Anikajain·Sep 18How I Distilled GPT-4o-mini Into a 1.5B Model on a 4 GB Laptop GPUA complete walkthrough of dataset distillation, QLoRA fine-tuning, DPO alignment, AWQ quantization and production serving, for $0.31 in API…
Ayşe Çetin·Aug 6GPT Türkçeyi Aslında Nasıl Görüyor?Biz tek bir cümle görüyoruz. Büyük dil modelleri ise aynı cümleyi, onlarca küçük parçadan oluşan bir sayı dizisi olarak görüyor.
Shiraz Muhammad·Aug 2AppForge: Smarter Android Code Reviews — Right on Your LaptopAI-powered quality checks for Android apps, without sending your code to the cloud.
Saniya Naphade·Jul 27What Is vLLM? A Hands-On Workshop with Qwen2.5-VL-7BWhy Another vLLM Post?A response icon1A response icon1
Nitin Mane·Jul 27Lets Built a Local Coding Assistant with Qwen2.5-Coder, OpenVINO, and INT4 CompressionHow to convert, compress, benchmark, and serve a code-specialized LLM on your own CPU or Intel GPU
