Dongfu Jiang's picture

Dongfu Jiang

DongfuJiang

·

https://jdf-prog.github.io/

AI & ML interests

Large Language Model, Modality Reasoning and their evaluation

Recent Activity

liked a model 23 days ago

TIGER-Lab/VisCoder-3B

upvoted a paper 23 days ago

VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation

upvoted a paper 23 days ago

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

View all activity

Organizations

DongfuJiang 's models 40

DongfuJiang/math_ct_adapt_qwen2.5_1.5B

2B • Updated Mar 6 • 11

DongfuJiang/math_ct_qwen2.5_1.5B

2B • Updated Mar 6 • 12

DongfuJiang/Qwen2-VL-VAE-7B-Instruct

Image-Text-to-Text • 8B • Updated Dec 17, 2024 • 11

DongfuJiang/Qwen2-VL-VAE-7B-Instruct-mochi-vae

Text2Text Generation • 8B • Updated Dec 17, 2024 • 42

DongfuJiang/qwen2_chunking_mlp_freeze_uniform_with_shared_start_and_end_2_12_pt

Text Generation • 0.7B • Updated Dec 9, 2024 • 36

DongfuJiang/qwen2_chunking_mlp_freeze_uniform_with_shared_start_and_end_2_12_sft

Text Generation • 0.7B • Updated Dec 9, 2024 • 27

DongfuJiang/qwen2_chunking_mlp_freeze_uniform_with_shared_start_and_end_2_6_pt

Text Generation • 0.6B • Updated Dec 9, 2024 • 35

DongfuJiang/qwen2_chunking_mlp_freeze_uniform_with_shared_start_and_end_2_6_sft

Text Generation • 0.6B • Updated Dec 9, 2024 • 32

DongfuJiang/qwen2_chunking_mlp_freeze_uniform_with_shared_start_pt

Text Generation • 0.5B • Updated Dec 7, 2024 • 24

DongfuJiang/qwen2_chunking_mlp_freeze_uniform_with_shared_start_sft

Updated Dec 7, 2024

DongfuJiang/prm_gsm_2k_with_full_sol_mix_ref_remove_all_correct_hf

Text Generation • 8B • Updated Dec 1, 2024 • 14 • 1

DongfuJiang/prm_qwen25_math_gsm_2k_with_full_sol_mix_ref_redistribution_hf

Text Generation • 8B • Updated Dec 1, 2024 • 17

DongfuJiang/prm_gsm_2k_with_full_sol_mix_ref_redistribution_hf

Text Generation • 8B • Updated Nov 30, 2024 • 16

DongfuJiang/prm_gsm_2k_with_full_sol_mix_ref_error_only_hf

Text Generation • 8B • Updated Nov 29, 2024 • 14

DongfuJiang/prm_qwen25_coder_version3_subsample_hf

Text Generation • 8B • Updated Nov 29, 2024 • 17

DongfuJiang/prm_qwen25_math_version3_subsample_hf

Text Generation • 8B • Updated Nov 28, 2024 • 18

DongfuJiang/prm_gsm_2k_with_full_sol_mix_ref_hf

Text Generation • 8B • Updated Nov 27, 2024 • 15

DongfuJiang/prm_math-l5_only

8B • Updated Nov 26, 2024 • 5

DongfuJiang/prm_version3_full_hf

Text Generation • 8B • Updated Nov 25, 2024 • 14

DongfuJiang/prm_gsm_all_data_bon_4_hf

Text Generation • 8B • Updated Nov 25, 2024 • 15

DongfuJiang/prm_math_only_hf

Text Generation • 8B • Updated Nov 25, 2024 • 16

DongfuJiang/prm_version3_subsample_no_ref_hf

Text Generation • 8B • Updated Nov 20, 2024 • 14

DongfuJiang/prm_version3_subsample_hf

Text Generation • 8B • Updated Nov 20, 2024 • 15

DongfuJiang/prm_version2_subsample_no_ref_hf

Text Generation • 8B • Updated Nov 18, 2024 • 15

DongfuJiang/Qwen2.5-0.5B-Instruct

Text Generation • 0.5B • Updated Nov 17, 2024 • 35

DongfuJiang/prm_version2_subsample_hf

Text Generation • 8B • Updated Nov 16, 2024 • 15

DongfuJiang/prm_version2_hf

Updated Nov 16, 2024

DongfuJiang/PairRM-V2-phi-3-4k-mini-all

Updated Aug 5, 2024 • 3

DongfuJiang/vapo_lora_all_data_iter_2

Updated Aug 1, 2024 • 3

DongfuJiang/vapo_lora_all_data_iter_1

Updated Jul 31, 2024 • 3