Kai Ye's picture

Open to Collab

4 1

Kai Ye

Kyleyee

·

https://noncollapse.github.io/

AI & ML interests

None yet

Recent Activity

updated a dataset 6 days ago

Kyleyee/eval-hh-clean

published a dataset 6 days ago

Kyleyee/eval-hh-clean

updated a dataset 6 days ago

Kyleyee/eval-hh-seed

View all activity

Organizations

Kyleyee 's models 181

Kyleyee/Qwen-GRPO-7B-1024bs-MATH-G4

Updated Dec 1, 2025

Kyleyee/Qwen-GRPO-7B-1024bs-MATH-G16

Updated Nov 30, 2025

Kyleyee/Qwen-GRPO-7B-1024bs-MATH-G128

Updated Nov 30, 2025

Kyleyee/qwen2_5-1.5b-grpo-riaid_v4

Text Generation • 2B • Updated Oct 21, 2025 • 1

Kyleyee/qwen2_5-1.5b-grpo-riaid_v3

Text Generation • 2B • Updated Oct 20, 2025 • 4

Kyleyee/qwen2_5-1.5b-grpo-riaid_v2

Text Generation • 2B • Updated Oct 19, 2025 • 2

Kyleyee/qwen2_5-1.5b-grpo-riaid_v1

Text Generation • 2B • Updated Oct 19, 2025 • 1

Kyleyee/qwen2_5-1.5b-sft-riaid_v2

Text Generation • 2B • Updated Oct 12, 2025 • 1

Kyleyee/qwen2_5-1_5b-sft-riaid_v1_shuffled

Text Generation • 2B • Updated Oct 12, 2025 • 1

Kyleyee/qwen2_5-1_5b-sft-riaid_v1

Text Generation • 2B • Updated Oct 12, 2025 • 1

Kyleyee/Qwen2.5-7b-sft-ultra-1e

Updated Aug 19, 2025

Kyleyee/Mistral-7B-Instruct-v0.3-vrpo

Text Generation • 266k • Updated Aug 16, 2025 • 2

Kyleyee/Qwen2.5-7b-dpo-imdb

Text Generation • 333k • Updated Jul 27, 2025 • 2

Kyleyee/Qwen2.5-7b-stf-imdb

Text Generation • 333k • Updated Jul 27, 2025 • 2

Kyleyee/Qwen2.5-1.5B-robustdpo-v2-hh

Text Generation • 2B • Updated Jul 26, 2025 • 2

Kyleyee/gpm_hh_3e_4dim

2B • Updated Jul 26, 2025 • 1

Kyleyee/gpm_hh_2e_2dim

2B • Updated Jul 26, 2025 • 1

Kyleyee/Qwen2.5-1.5B-ropo-hh

Text Generation • 2B • Updated Jul 25, 2025 • 2

Kyleyee/Qwen2.5-1.5B-cdpo-hh

Text Generation • 2B • Updated Jul 25, 2025 • 2

Kyleyee/Qwen2.5-1.5B-SimPO-hh

Text Generation • 2B • Updated Jul 25, 2025 • 1

Kyleyee/Qwen2.5-1.5B-cpo-hh

Text Generation • 2B • Updated Jul 25, 2025 • 1

Kyleyee/Qwen2.5-1.5B-robustdpo-hh

Text Generation • 2B • Updated Jul 25, 2025 • 2

Kyleyee/Qwen2.5-7B-ppo-hh

Updated Jul 23, 2025

Kyleyee/Qwen2.5-7B-reward-hh

337k • Updated Jul 15, 2025 • 1

Kyleyee/Qwen2.5-7b-sft-hh

Text Generation • 8B • Updated Jul 14, 2025 • 2

Kyleyee/EleutherAI_pythia-1b-deduped_tldr_ppo_ml

Text Generation • 1B • Updated May 12, 2025 • 2

Kyleyee/EleutherAI_pythia-1b-deduped_tldr_ppo_ms

Text Generation • 1B • Updated May 12, 2025 • 2

Kyleyee/gpt-neo-125m-dpo-imdb

Text Generation • 0.1B • Updated May 10, 2025 • 1

Kyleyee/gpt-neo-125m-stf-imdb

Text Generation • 0.1B • Updated May 10, 2025 • 4

Kyleyee/EleutherAI_pythia-1b-deduped_tldr_ppo

Text Generation • 1B • Updated May 9, 2025 • 2