-
Preference Fine-Tuning LFM 2 Using DPO
Learn how to fine-tune Liquid Foundation Models (LFM 2) using Direct Preference Optimization for efficient, edge-ready small language models.
Shaik Hamzah 07 Jan, 2026
-
Google T5Gemma-2 Explained: Trying Out a Laptop-Friendly Multimodal AI Model
Explore Google T5Gemma-2, a compact multimodal AI model with long context and laptop-friendly performance, with a hands-on demo.
Soumil Jain 01 Jan, 2026
-
Less is More: Recursive Reasoning with Tiny Networks
Explore how a TRM is able to achieve maximal reasoning through minimal architecture, proving to be a viable alternative to HRMs
Vipin Vashisth 24 Oct, 2025
-
10 Cool Tricks Modern LLM Design Uses
A modern LLM is no longer about more GPUs, it uses clever design tricks for effective results. Read on to find out what these are
Mohd Sanad Zaki Rizvi 12 Oct, 2025
-
Github Repository for Top LLM Datasets
Explore the Github Repository for LLM Datasets and transform your AI projects with quality data for model training.
Riya Bansal. 21 Sep, 2025
-
Better Than GPT-5? We Try ERNIE X1.1, Baidu’s Latest AI Model
In this hands-on, we try the capabilities of ERNIE X1.1, Baidu's latest model focusing on practical reliability and reasoning-first design.
Sarthak Dogra 11 Sep, 2025
-
How to Build a RAG Using Qwen3?
Explore the two newly launched Qwen3 models while using their impressive context lengths to build a RAG model
Mounish V 21 Aug, 2025
-
Mastering Decoder-Only Transformer: A Comprehensive Guide
Explore Decoder-Only Transformer: attention, normalization, classification. Master text generation & translation.
Sahitya Arya 26 Apr, 2024
