Cerebras REAP Collection Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method β’ 26 items β’ Updated about 17 hours ago β’ 96
Kimi-K2 Collection Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence β’ 5 items β’ Updated 1 day ago β’ 165
view article Article Building a Real-Time Video Chat with Gemini 2.0, Gradio, and WebRTC ππ Jan 13, 2025 β’ 9
view article Article Introducing smolagents: simple agents that write actions in code. +1 Dec 31, 2024 β’ 1.16k
Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step Paper β’ 2501.13926 β’ Published Jan 23, 2025 β’ 43
view article Article πΊπ¦ββ¬ LLM Comparison/Test: Phi-4, Qwen2 VL 72B Instruct, Aya Expanse 32B in my updated MMLU-Pro CS benchmark Jan 10, 2025 β’ 8
LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context Paper β’ 2412.17596 β’ Published Dec 23, 2024 β’ 6