In a Training Loop 🔄
lewtun
·
AI & ML interests
LLMs, LLMs, LLMs
Organizations
lewtun/dolci-think-sft-6400
Viewer
• Updated • 6.4k • 29
lewtun/dolci-think-sft-3200
Viewer
• Updated • 3.2k • 27
lewtun/dolci-think-sft-1600
Viewer
• Updated • 1.6k • 28
lewtun/dolci-think-sft-800
Viewer
• Updated • 800 • 28
lewtun/dolci-think-sft-400
Viewer
• Updated • 400 • 31
lewtun/dolci-think-sft-200
Viewer
• Updated • 200 • 29
lewtun/s1K-1.1-dataforge-testing-20251219-213939
Viewer
• Updated • 1k • 34
lewtun/s1K-1.1-dataforge-testing-20251219-081400
Viewer
• Updated • 819 • 37
lewtun/s1K-1.1-dataforge-testing-20251218-204703
Viewer
• Updated • 920 • 219
lewtun/dataforge-testing-20251218-152114
Viewer
• Updated • 1k • 92
lewtun/s1K-1.1-dataforge-testing-20251216-142704
Viewer
• Updated • 10 • 18
lewtun/s1K-1.1-dataforge-testing-20251216-123019
Viewer
• Updated • 1k • 83
lewtun/Polaris-Dataset-53K
Viewer
• Updated • 53.3k • 49
lewtun/details_meta-llama__Llama-2-7b-chat-hf_private
Viewer
• Updated • 7.21k • 50
lewtun/OpenThoughts3-missing-think-sample
Viewer
• Updated • 100 • 9
lewtun/details_Qwen__Qwen2.5-Coder-3B-Instruct
Viewer
• Updated • 33 • 27
lewtun/details_deepseek-ai__DeepSeek-R1-Distill-Qwen-1.5B
Viewer
• Updated • 1k • 18
lewtun/details_open-thoughts__OpenThinker-7B
Viewer
• Updated • 597 • 31
lewtun/details_deepseek-ai__DeepSeek-R1-Distill-Qwen-7B
Viewer
• Updated • 597 • 32
lewtun/details_meta-llama__Llama-3.2-3B-Instruct
Viewer
• Updated • 1.74k • 15
lewtun/details_deepseek-ai__DeepSeek-R1-Distill-Llama-8B
Viewer
• Updated • 598 • 20
lewtun/details_meta-llama__Llama-3.1-8B-Instruct
Viewer
• Updated • 597 • 10
lewtun/details_Qwen__Qwen2.5-1.5B-Instruct
Viewer
• Updated • 2.25k • 20
lewtun/details_Qwen__Qwen2.5-0.5B-Instruct
Viewer
• Updated • 898 • 11
lewtun/details_meta-llama__Llama-3.2-1B-Instruct
Viewer
• Updated • 898 • 6
lewtun/details_Qwen__Qwen2.5-Math-1.5B-Instruct
Viewer
• Updated • 11k • 9
Viewer
• Updated • 1 • 5
lewtun/Llama-3.2-1B-Instruct-best_of_n-prm-completions
Viewer
• Updated • 10 • 6
Preview
• Updated • 109