DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
By
•
•
1
Community Articles
view allDeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
By
•
•
1Building an African Cultural Dataset with SmoLAgents: Experimental
By
•
Distributed SFT with trl and DeepSpeed Part 2: Scaling Locally
By
•
•
1AI Bookkeeper: Enhancing Accounting Document Understanding Through Supervised Fine-Tuning
By
and 1 other
•
•
3Bringing Multi-Agent AI to JavaScript with KaibanJS
By
•
•
1What is test-time compute and how to scale it?
By
and 1 other
•
•
9Agentic RAG Stack (3/5) - Generate responses using a SmolLM
By
•
•
6G2P Shrinks Speech Models
By
•
•
16Build Your Own AI Tutor with Streamlit and OpenAI
By
•
Agentic RAG Stack (2/5) - Augment retrieval results by reranking using Sentence Transformers
By
•
•
6Automating Sports News Reporting with AI Agents in KaibanJS
By
•
•
1AI Agents for Hardware Optimization: Automating PC Gaming Performance with KaibanJS
By
•
•
1Assessment of how well Large Language Models (LLMs) answer questions related to gender equality and women’s empowerment
By
and 2 others
•
A Review on the Evolvement of Load Balancing Strategy in MoE LLMs: Pitfalls and Lessons
By
•
From Zero to Reasoning Hero: How DeepSeek-R1 Leverages Reinforcement Learning to Master Complex Reasoning
By
•
•
2MLA: Redefining KV-Cache Through Low-Rank Projections and On-Demand Decompression
By
•
•
3syncIAL🍏: A Multi-Purpose Synthetic Debate and Argument Mapping Corpus
By
•
•
2Smol but Mighty: Can Small Models Reason well? 🤔
By
•
•
7AI Agents for Company Research: Automating Business Analysis with KaibanJS
By
•
•
1From Hippocrates to AI: Reflections on the Evolution of Consent
By
•
•
8