Running 114 Unlocking On-Policy Distillation for Any Model Family π 114 Explore on-policy distillation visualization for any model
Running on CPU Upgrade Featured 3.22k The Smol Training Playbook π 3.22k The secrets to building world-class LLMs
Running 601 Scaling test-time compute π 601 Boost LLM answers with flexible testβtime search strategies
Running on Zero Agents Featured 826 Qwen Image Edit β 826 Edit images using natural language instructions
meta-llama/Llama-3.2-1B-Instruct Text Generation β’ 1B β’ Updated Oct 24, 2024 β’ 8.4M β’ β’ 1.5k