Fangkai Jiao's picture

1 4 16

Fangkai Jiao

chitanda

·

https://jiaofangkai.com/

SparkJiao

AI & ML interests

self-supervised pre-training, large language model and machine reasoning.

Recent Activity

authored a paper about 3 hours ago

Preference Optimization for Reasoning with Pseudo Feedback

upvoted a collection about 10 hours ago

updated a dataset about 10 hours ago

chitanda/code-synthetic-test-cases

View all activity

Organizations

Collections 1

Papers 16

arxiv:2411.16345

arxiv:2410.01428

arxiv:2404.14604

arxiv:2404.12728

models 82

chitanda/gemma.2b.it.meta_math_distil.H100.w4.v1.0

Updated May 16, 2024

chitanda/gemma.2b.it.meta_math_rap.dpo.H100.w4.v1.1.fix.s42

Updated Apr 26, 2024

chitanda/llama2.7b.chat.logiqav2.70b-distil.step.dpo.fix_hack.H100.w4.v1.0.th.s43

Updated Apr 11, 2024

chitanda/llama2.7b.chat.logiqav2.70b-distil.step.dpo.fix_hack.H100.w4.v1.0.th.s42

Updated Apr 11, 2024

chitanda/llama2.7b.chat.logiqav2.70b-distil.step.dpo.fix_hack.A100.w4.v1.0.th.s44

Updated Apr 11, 2024

chitanda/llama2.7b.chat.logiqav2.70b-distil.prm.fix_hack.H100.w4.v2.0.s42

Updated Apr 9, 2024

chitanda/llama2.7b.chat.reclor.gpt35turbo1106.dpo-sft.H100.w4.v2.0

Updated Apr 5, 2024

chitanda/llama2.7b.chat.logiqav2.70b-distil.prm.fix_hack.A100.w4.v1.2.s42

Updated Apr 4, 2024

chitanda/llama2.7b.chat.logiqav2.70b-distil.dpo.fix_hack.H100.w4.v1.0.th.test.s43

Updated Mar 30, 2024

chitanda/llama2.7b.chat.logiqav2.llama-2-70b-chat.dpo-sft.A6K.w4.v1.0

Updated Mar 16, 2024

datasets 5

chitanda/code-synthetic-test-cases

Preview • Updated about 10 hours ago • 2

chitanda/mathscale4o-800k

Viewer • Updated about 14 hours ago • 492k • 1

chitanda/deepseek-math.7b.ins.completion_data

Preview • Updated Sep 29, 2024 • 52

chitanda/dpo-reasoning-trajectory

Preview • Updated Feb 2, 2024 • 135 • 2

chitanda/wiki_erica_path_v9.1

Updated Oct 27, 2023 • 67 • 1