Announcing MamayLM, an efficient state-of-the-art Ukrainian LLM
By
and 2 others
•
•
37
Announcing MamayLM, an efficient state-of-the-art Ukrainian LLM
By
and 2 others
•
•
37🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?
By
•
•
204Gotchas in Tokenizer Behavior Every Developer Should Know
By
•
•
26An Introduction to AI Model Optimization Techniques
By
and 1 other
•
•
25Uncensor any LLM with abliteration
By
•
•
524FramePack LoRA Experiment
By
•
•
13MamayLM, передова мовна модель для української мови
By
and 2 others
•
•
13How to Use FastAPI MCP Server: A Complete Guide
By
•
•
20Consent by Design: Approaches to User Data in Open AI Ecosystems
By
and 1 other
•
•
10DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
By
•
•
116Reasoning Datasets Competition
By
and 6 others
•
•
24🏆 Mistral AI Robotic Hackathon – 2nd Place: “LeCopain” 🤖
By
and 4 others
•
•
7Finetuning olmOCR to be a faithful OCR-Engine
By
and 1 other
•
•
7Framepack : groundbreaking video generation technology whose model size is only 0.13B parameters.
By
•
•
7Optimise AI Models and Make Them Faster, Smaller, Cheaper, Greener
By
and 2 others
•
•
18What is The Agent2Agent Protocol (A2A) and Why You Must Learn It Now
By
•
•
8🔥 Announcing FLUX-Juiced: The Fastest Image Generation Endpoint (2.6 times faster)!
By
and 3 others
•
•
6What is test-time compute and how to scale it?
By
and 1 other
•
•
76Comparing sub 50GB Llama 4 Scout quants (KLD/Top P)
By
•
•
37Fine-tuning SmolLM with Group Relative Policy Optimization (GRPO) by following the Methodologies
By
•
•
19