Runpeng Geng

sleeepeer 's models 171

Sort:  Recently updated

sleeepeer/Llama-3.1-8B-Instruct-GRPO-alpaca_mix_combine_naive_least_similar-llm-judge-42

Text Generation • 8B • Updated Jul 16, 2025 • 4

sleeepeer/Llama-3.1-8B-Instruct-GRPO-alpaca-mix-injected-llm-judge-42

Updated Jul 15, 2025

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-alpaca-mix-injected-llm-judge-42

8B • Updated Jul 14, 2025 • 2

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-alpaca-mix-injected-llm-judge-42-checkpoint-3000

Updated Jul 14, 2025

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-alpaca-mix-injected-llm-judge-42-checkpoint-4000

Updated Jul 14, 2025

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-mixed-clean-1000-llm-judge-42

8B • Updated Jul 10, 2025 • 1

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-mixed-llm-judge-42

Text Generation • 8B • Updated Jul 10, 2025 • 3

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-mixed-cosine-42

Text Generation • 8B • Updated Jul 9, 2025 • 4

sleeepeer/Meta-Llama-3-8B-Instruct-DPO-mixed-42

Text Generation • 8B • Updated Jul 8, 2025 • 3

sleeepeer/Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-2-AT-7

Text Generation • 8B • Updated Jul 7, 2025 • 4

sleeepeer/Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-2-AT-6

Text Generation • 8B • Updated Jul 7, 2025 • 3

sleeepeer/Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-2-AT-5

Text Generation • 8B • Updated Jul 6, 2025 • 5

sleeepeer/Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-2-AT-4

Text Generation • 8B • Updated Jul 6, 2025 • 4

sleeepeer/Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-2-AT-3

Text Generation • 8B • Updated Jul 6, 2025 • 4

sleeepeer/Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-2-AT-2

Text Generation • 8B • Updated Jul 6, 2025 • 3

sleeepeer/Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-2-AT-1

Text Generation • 8B • Updated Jul 5, 2025 • 2

sleeepeer/Llama-3.1-8B-Instruct-GRPO-AT-short-10-NEW-TRAIN-directly-output-easy-AT-1

Text Generation • 8B • Updated Jul 5, 2025 • 5

sleeepeer/Llama-3.1-8B-Instruct-GRPO-alpaca-combine-100-no-KL-42

8B • Updated Jul 5, 2025 • 2

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-hard-AT-4

Text Generation • 8B • Updated Jul 3, 2025 • 4

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-easy-AT-4

Text Generation • 8B • Updated Jul 3, 2025 • 3

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-hard-AT-3

Text Generation • 8B • Updated Jul 3, 2025 • 4

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-easy-AT-3

Text Generation • 8B • Updated Jul 2, 2025 • 3

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-hard-AT-2

Text Generation • 8B • Updated Jul 2, 2025 • 4

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-easy-AT-2

Text Generation • 8B • Updated Jul 2, 2025 • 4

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-hard-AT-1

Text Generation • 8B • Updated Jul 1, 2025 • 4

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-directly-output-easy-AT-1

Text Generation • 8B • Updated Jul 1, 2025 • 4

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-AT-3

Text Generation • 8B • Updated Jul 1, 2025 • 4

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-16-NEW-TRAIN-new-reward-AT-3

Text Generation • 8B • Updated Jul 1, 2025 • 3

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-20-NEW-TRAIN-AT-2

Text Generation • 8B • Updated Jul 1, 2025 • 4

sleeepeer/Meta-Llama-3-8B-Instruct-GRPO-AT-short-16-NEW-TRAIN-new-reward-AT-2

Text Generation • 8B • Updated Jul 1, 2025 • 4