There is no such thing as a tokenizer-free lunch
By
•
•
61Nemotron-Personas-Japan: Synthesized Data for Sovereign AI
By
and 6 others
•
•
22RexBERT: Encoders for a brave new world of E-Commerce
By
and 1 other
•
•
44Model Quality: Hugging Face Is All You Need
By
•
•
14Qianfan-VL: A Milestone Achievement in Chinese Multimodal AI with Domestic Chips
By
•
•
8Code a simple RAG from scratch
By
•
•
204PP-OCRv5 on Hugging Face: A Specialized Approach to OCR
By
and 5 others
•
•
102Ground-up efforts to build large datasets for effective and accurate translation of Modi-Script documents into modern Marathi
By
and 1 other
•
•
6Nemotron-Personas-Japan: ソブリン AI のための合成データセット
By
and 6 others
•
•
6Uncensor any LLM with abliteration
By
•
•
682DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
By
•
•
225🌎 What kind of environmental impacts are AI companies disclosing? (And can we compare them?) 🌎
By
and 1 other
•
•
12Preserving Agency: Why AI Safety Needs Community, Not Corporate Control
By
•
•
5Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face
By
•
•
70Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
By
•
•
71Small Language Models (SLM): A Comprehensive Overview
By
•
•
74Understanding Gemma 3n: How MatFormer Gives You Many Models in One
By
•
•
47PrediBench: Testing AI models on prediction markets
By
and 1 other
•
•
4Mastering Tensor Dimensions in Transformers
By
•
•
98Prefill and Decode for Concurrent Requests - Optimizing LLM Performance
By
•
•
43