shengzhi alex li's picture

6 1 5

shengzhi alex li

alexshengzhili

·

https://scholar.google.com/citations?user=UBxhmfIAAAAJ&hl=en&oi=ao

AI & ML interests

None yet

Recent Activity

commented on a paper 4 days ago

Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy

updated a model 2 months ago

alexshengzhili/testing_lora

published a model 2 months ago

alexshengzhili/testing_lora

View all activity

Organizations

alexshengzhili 's models 72

alexshengzhili/testing_lora

alexshengzhili/qwen2_5_vl_7b_repcount

8B • Updated Apr 30 • 79

alexshengzhili/Qwen2.5-3B-Open-R1-Code-GRPO-r2

Text Generation • 3B • Updated Mar 14 • 15

alexshengzhili/Qwen2.5-1.5B-Open-R1-Code-GRPO-r2

2B • Updated Mar 12 • 11

alexshengzhili/Qwen-2.5-7B-Simple-RL

alexshengzhili/Qwen2.5-7B-Open-R1-Code-GRPO-r2

alexshengzhili/Qwen2.5-1.5B-Open-R1-Code-GRPO

alexshengzhili/llama3_8b_dpo_0908_preference_4_conference_shuffled_2023

Text Generation • 8B • Updated Sep 11, 2024 • 7

alexshengzhili/mistral_3_0908_preference_4_conference_shuffled_2023_sft

Text Generation • 7B • Updated Sep 10, 2024 • 8

alexshengzhili/dpo_0908_preference_4_conference_shuffled_2023_checkpoint_30

Text Generation • 7B • Updated Sep 10, 2024 • 6

alexshengzhili/phi3-dpo_0908_preference_4_conference_shuffled_2023

Text Generation • 4B • Updated Sep 9, 2024 • 9

alexshengzhili/phi3-dpo_0907_preference_iclr2023

Text Generation • 4B • Updated Sep 8, 2024 • 7

alexshengzhili/llama3.1-8b-lora_dpo_0907_preference_iclr2023

Text Generation • 8B • Updated Sep 8, 2024 • 6

alexshengzhili/llama3.1-8b-0806_iclr2023_cleaned

Text Generation • 8B • Updated Aug 21, 2024 • 8

alexshengzhili/phi3-0806_iclr2023_cleaned

Text Generation • 4B • Updated Aug 21, 2024 • 8

alexshengzhili/phi3-0608_all_of_train-dpo-merged

Text Generation • 4B • Updated Jun 15, 2024 • 7

alexshengzhili/ph3-0607-lora-dpo-beta-0dot1-merged

Text Generation • 4B • Updated Jun 14, 2024 • 6

alexshengzhili/ph3-0606-lora-dpo-beta-0dot2-merged

Text Generation • 4B • Updated Jun 14, 2024 • 11

alexshengzhili/ph3-0606-lora-dpo-merged

Text Generation • 4B • Updated Jun 14, 2024 • 8

alexshengzhili/ph3-0606-lora-sft-merged

Text Generation • 4B • Updated Jun 13, 2024 • 8

alexshengzhili/llava-v1.5-13b-dpo

Text Generation • Updated Apr 13, 2024 • 8 • 5

alexshengzhili/llava-dpo-13b

Text Generation • Updated Jan 31, 2024 • 11

alexshengzhili/llava-dpo-13b-lora

Updated Jan 31, 2024

alexshengzhili/llava-lora-dpo-1227lrvtail2000_from_sft-self-sampled-beta-0.5-lr-5e-5-avg-False-epoch-3

Updated Dec 29, 2023 • 2

alexshengzhili/llava-v1.5-13b-lora-coh-interleaf-lrv1500llava2000

Updated Dec 29, 2023 • 2

alexshengzhili/llava-v1.5-13b-lora-1227-COH-lrv0-3230llava0-5879_interleaved.json

Updated Dec 29, 2023 • 22

alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.5-lr-5e-6-avg-False-epoch-3

Updated Dec 28, 2023

alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.5-lr-5e-6-avg-False-epoch-2

Updated Dec 28, 2023

alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.5-lr-5e-5-avg-False-epoch-3

Updated Dec 28, 2023

alexshengzhili/llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.5-lr-5e-5-avg-False-epoch-2

Updated Dec 28, 2023