Running Featured 473 Jev Decision Index π¬ 473 Benchmarks and news on various repros of TypeSafe's Jev
Running 4.07k The Ultra-Scale Playbook π 4.07k The ultimate guide to training LLM on large GPU Clusters
Running 19 Defeating the trainer-generator precision mismatch in TRL π― 19 Download research PDF (Pro access required)
OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview Image-Text-to-Text β’ 0.4B β’ Updated Aug 29, 2025 β’ 17.4k β’ 86
meta-llama/Llama-3.2-1B-Instruct Text Generation β’ 1B β’ Updated Oct 24, 2024 β’ 7.5M β’ β’ 1.79k
deepseek-ai/DeepSeek-R1-0528 Text Generation β’ 685B β’ Updated May 29, 2025 β’ 205k β’ β’ 2.47k
Paused Agents 9 Flux Quantized or Original? π 9 Generate and compare quantized images from prompts