BozhongXiao's picture

BozhongXiao

Atomheart-Father

·

Atomheart-Father

AI & ML interests

LLM

Organizations

models 6

Atomheart-Father/llama_ppo_stage_0

Atomheart-Father/llama-sft-stage0

Atomheart-Father/llama32-1b-thinkfinal-sft

Text Generation • 1B • Updated Jan 12 • 1

Atomheart-Father/small_change_sft_dpo

Atomheart-Father/rc1-qwen3-4b-thinking-gemini

Updated Aug 21, 2025

Atomheart-Father/ppo-LunarLander-v2

Reinforcement Learning • Updated Nov 22, 2023

datasets 4

Atomheart-Father/ppo_ppl_thinkfinal_stage10

Viewer • Updated Jan 12 • 21k • 27

Atomheart-Father/small_change_sft_dpo

Preview • Updated Jan 12 • 24

Atomheart-Father/sft_pool_3300_thinkfinal_1024

Viewer • Updated Jan 12 • 2.87k • 9

Atomheart-Father/ppo_pool_24000_ppl10_sys10_thinkfinal_toklen

Viewer • Updated Jan 12 • 21k • 19