Thrillcrazyer/Qwen1.7_final
Updated • 39
TaekHyunPark
Thrillcrazyer
AI & ML interests
Novel Architecture, Sequential Modeling
Recent Activity
liked a model 8 days ago
SofiTesfay2010/scientific-reasoning-training upvoted a paper 8 days ago
AI scientists produce results without reasoning scientifically updated a model 15 days ago
Thrillcrazyer/Qwen1.7_finalOrganizations
None yet
Thrillcrazyer/Qwen1.7_01234
Updated • 32
Thrillcrazyer/TinyLlama_v1.1
Updated • 26
Thrillcrazyer/QWEN3-8B_LDS_ver2
Updated • 58
Thrillcrazyer/PHI4_LDS
Updated • 48
Thrillcrazyer/SFT_LDS_QWEN1.7B
Updated • 6
Thrillcrazyer/LDS-1.7B_verSoftPLUS
Updated • 20
Thrillcrazyer/Qwen4B_ver0.2
Updated • 92 • 1
Thrillcrazyer/Qwen3-1.7B_ver0.2_5000
Updated • 84
Thrillcrazyer/Qwen3-1.7B_LDS_NO_RAND
Updated • 1
Thrillcrazyer/Qwen3-1.7B_LDS_NO_ENCDEC
Updated • 3
Thrillcrazyer/Qwen3-1.7B_LDS_SELU
Updated • 1
Thrillcrazyer/QWEN3-1.7B_LDS_forgot
Updated • 4
Thrillcrazyer/QWEN3-1.7B_LDS_ver2
Updated • 3
Thrillcrazyer/QWEN3-1.7B_LDS
Updated • 21
Thrillcrazyer/Qwen-2.5-1.5B_TAC_Teacher_LLAMA70
Text Generation • 2B • Updated • 94 •
Thrillcrazyer/Qwen-2.5-1.5B_TAC_Teacher_Qwen14B
Text Generation • 2B • Updated • 88 •
Thrillcrazyer/Qwen-2.5-1.5B_TAC_Teacher_Qwen32B
Text Generation • 2B • Updated • 89 •
Thrillcrazyer/Qwen-2.5-1.5B_TAC_Teacher_Qwen14B_Extractor_Qwen72B
Updated
Thrillcrazyer/Qwen-7B_PRMLM_GSPO
Text Generation • 8B • Updated • 47
Thrillcrazyer/QWEN3-8B_LDS
Updated • 1
Thrillcrazyer/QWEN3-1.7B_LDS_NO_A
Updated
Thrillcrazyer/LDS_4B
Updated • 3
Thrillcrazyer/LDS_1.8B
Updated
Thrillcrazyer/TACReward7B
Text Generation • 333k • Updated • 5 • 6
Thrillcrazyer/Qwen-7B_Fitness_GSPO
Text Generation • 333k • Updated • 3
Thrillcrazyer/Qwen-7B_Precision_GSPO
Text Generation • 333k • Updated • 1
Thrillcrazyer/Qwen-7B_TAC_PPO
Text Generation • 333k • Updated • 1
Thrillcrazyer/Qwen-7B_NOTAC_PPO
Text Generation • 333k • Updated • 2
Thrillcrazyer/Qwen-7B_NOTAC_RLOO
Text Generation • 8B • Updated • 2