Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 30 items • Updated 17 days ago • 130
Kimi-K2 Collection Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence • 5 items • Updated Jan 27 • 172
view article Article Building a Real-Time Video Chat with Gemini 2.0, Gradio, and WebRTC 👀👂 Jan 13, 2025 • 9
view article Article Introducing smolagents: simple agents that write actions in code. +1 Dec 31, 2024 • 1.18k
Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step Paper • 2501.13926 • Published Jan 23, 2025 • 43
view article Article 🐺🐦⬛ LLM Comparison/Test: Phi-4, Qwen2 VL 72B Instruct, Aya Expanse 32B in my updated MMLU-Pro CS benchmark Jan 10, 2025 • 8
LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context Paper • 2412.17596 • Published Dec 23, 2024 • 6