Refreshing zero-shot classification with ModernBERT
By
•
•
3Distilling from Dialogues: Finding Meaning in LLM Interactions
By
•
•
4🌁#89: AI in Action: How AI Engineers, Self-Optimizing Models, and Humanoid Robots Are Reshaping 2025
By
•
•
4Online Batch Size Adaptation in Hugging Face Trainer
By
•
AI, Data Privacy and Religious Tolerance: Building a Harmonious Digital Future
By
•
•
1🦸🏻#11: How Do Agents Plan and Reason?
By
•
•
15Small Language Models (SLM): A Comprehensive Overview
By
•
•
71Open Source AI Agents | Github/Repo List | [2025]
By
•
•
29Topic 28: What is Mixture-of-Mamba?
By
and 1 other
•
•
3Mimicking Consciousness in LLMs: Ascending the Dimensions of Thought with Recurrent Processing
By
•
•
3结合Deepseek代码探讨MLA的改进及收益
By
•
•
6大模型偏好优化技术：DPO及其变种
By
•
•
13Argunauts Training Phase II: Selfplay Finetuning Line-By-Line
By
•
•
5Synthetic Face Embeddings: Research Notes and Methodology
By
and 1 other
•
•
6How to use Sentient’s Dobby-70B
By
•
Mahjong: Where Grandmas Beat The Best LLMs
By
•
•
9Mixture of Tunable Experts - Behavior Modification of DeepSeek-R1 at Inference Time
By
and 4 others
•
•
34Argunauts Training Phase I: Continual Pretraining on Synthetic Data
By
•
•
2Best AI Setups for Multi-Agent Workflows in KaibanJS
By
•
🌁#88: Can DeepSeek Inspire Global Collaboration?
By
•
•
3