edbeeching
·
AI & ML interests
None yet
Organizations
edbeeching/Qwen3-0.6B-GKD-simple-gold-qwen3-4b-exacttoken
Updated
edbeeching/Qwen3-0.6B-GKD-simple-gold-top1-qwen3-1p7b-teacher
Updated
edbeeching/Qwen3-0.6B-GKD-simple-gold-top1-qwen3-4b-teacher
Updated
edbeeching/Qwen3-0.6B-GKD-simple-gold-topk
Updated
edbeeching/Qwen3-0.6B-GKD-simple-gold2
Updated
edbeeching/Qwen3-4B-Base-SFT-tr5
Text Generation
• 4B • Updated • 15
• edbeeching/Qwen3-4B-Instruct-2507-SFT-tr5
Text Generation
• 4B • Updated • 24
• edbeeching/Qwen3-4B-Thinking-2507-SFT-tr5
Text Generation
• 4B • Updated • 8
• edbeeching/Qwen3-0.6B-GKD-simple-gold
Updated
edbeeching/Qwen3-4B-GKD-simple-gold
Updated
edbeeching/Qwen3-0.6B-GKD-simple
Updated
edbeeching/Qwen3-4B-GKD-simple
Updated
edbeeching/Qwen3-4B-GKD-push
Updated
edbeeching/pipeline-trl-push-callback-smoke-20260317t210929z
Updated
edbeeching/pipeline-trl-test
Updated
edbeeching/Qwen3-0.6B-untied
Text Generation
• 0.8B • Updated • 5
• edbeeching/fixed-Qwen3-30B-A3B-Thinking-2507-SFT-v03.01-step-000000062
Text Generation
• 31B • Updated • 2
edbeeching/Qwen3-30B-A3B-Thinking-2507-trans-5.0-format
Text Generation
• 31B • Updated • 6
edbeeching/Qwen2.5-1.5B-Open-R1-Distill-dev
Updated
edbeeching/OpenR1-Distill-7B-packing-benchmarks
8B • Updated • 6
edbeeching/OpenR1-Distill-7B
Text Generation
• 8B • Updated • 13
edbeeching/SmolLM3-3B-instruct
Updated
edbeeching/Qwen2.5-1.5B-Open-R1-Distill
Text Generation
• 2B • Updated • 10
edbeeching/DeepScaler-DeepSeek-R1-Distill-Qwen-1.5B-GRPO
2B • Updated • 1
edbeeching/Qwen2.5-7B-Instruct-GRPO
8B • Updated • 4
edbeeching/Qwen2.5-Math-7B-Instruct-SFT
Text Generation
• 8B • Updated • 2
edbeeching/Qwen2.5-1.5B-Open-R1-Code-GRPO
Updated
edbeeching/Qwen2.5-Coder-3B-Instruct-sft
Text Generation
• 3B • Updated • 6
edbeeching/pythia-1b-deduped-tldr-online-dpo
Updated