JayHyeon/Qwen_0.5-cDPO_5e-7_1.0vpo_constant_0.1label_smoothing
Text Generation
•
0.6B
•
Updated
•
10
JaeHyeon Cho
JayHyeon
AI & ML interests
None yet
Recent Activity
updated
a model
29 days ago
JayHyeon/Qwen_0.5-VDPO_5e-7_5vpo_constant_ls0.0_seed42
updated
a model
29 days ago
JayHyeon/Qwen_0.5-VDPO_5e-7_3.0vpo_constant_ls0.0_seed42
updated
a model
29 days ago
JayHyeon/Qwen_0.5-VDPO_5e-7_0.3vpo_constant_ls0.0_seed42
Organizations
None yet
JayHyeon/Qwen_0.5-DPO_5e-7_1.0vpo_constant
Text Generation
•
0.6B
•
Updated
•
9
JayHyeon/Qwen_3B-DPO_5e-7_1.0vpo_constant-1ep
Updated
JayHyeon/qwen_0.5-DPO_5e-7_1.0vpo_constant-1ep
Updated
JayHyeon/Llama-DPO_5e-7_1.0vpo_constant-1ep
Updated
JayHyeon/Qwen_0.5-DPO_3e-6_1.0vpo_constant-1ep
Updated
JayHyeon/pythia-2.8b-rDPO_5e-7_1.0vpo_constant-1ep_0.3label_smoothing
Text Generation
•
3B
•
Updated
•
10
JayHyeon/pythia-2.8b-cDPO_5e-7_1.0vpo_constant-1ep_0.3label_smoothing
Text Generation
•
3B
•
Updated
•
10
JayHyeon/pythia-2.8b-rDPO_5e-7_1.0vpo_constant-1ep_0.1label_smoothing
Text Generation
•
3B
•
Updated
•
12
JayHyeon/pythia-2.8b-cDPO_5e-7_1.0vpo_constant-1ep_0.1label_smoothing
Text Generation
•
3B
•
Updated
•
9
JayHyeon/pythia-2.8b-2e-5-1ep
Text Generation
•
3B
•
Updated
•
10
JayHyeon/Qwen_1.5B-math-rDPO_5e-7_0.3lsmooth-1.0vpo_constant-1ep
Text Generation
•
2B
•
Updated
•
9
JayHyeon/Qwen_1.5B-math-rDPO_5e-7_0.1lsmooth-1.0vpo_constant-1ep
Text Generation
•
2B
•
Updated
•
10
JayHyeon/Qwen_1.5B-math-cDPO_5e-7_0.3lsmooth-1.0vpo_constant-1ep
Text Generation
•
2B
•
Updated
•
9
JayHyeon/Qwen_1.5B-math-cDPO_5e-7_0.1lsmooth-1.0vpo_constant-1ep
Text Generation
•
2B
•
Updated
•
10
JayHyeon/Qwen_1.5B-math-cDPO_5e-7_1.0vpo_constant-1ep
Updated
JayHyeon/Qwen_0.5-ultrainteract_SPPO_5e-7-1ep
Text Generation
•
0.6B
•
Updated
•
12
JayHyeon/Qwen_0.5-ultrainteract_SLiC_5e-7-1ep
Text Generation
•
0.6B
•
Updated
•
12
JayHyeon/llama-DPOP_3e-6-1ep_0alp_0.5bdpo_lam_5dpop_lam
Updated
JayHyeon/llama-IRPO_3e-6-1ep_1alp_0.5bdpo_lam_0dpop_lam
Text Generation
•
1B
•
Updated
•
13
JayHyeon/llama-BDPO_3e-6-1ep_0alp_0.5bdpo_lam_0dpop_lam
Text Generation
•
1B
•
Updated
•
12
JayHyeon/llama-DPO_1e-6-1ep_0alp_0.5bdpo_lam_0dpop_lam
Text Generation
•
1B
•
Updated
•
10
JayHyeon/llama-DPOP_1e-6-1ep_0alp_0.5bdpo_lam_5dpop_lam
Text Generation
•
1B
•
Updated
•
14
JayHyeon/llama-IRPO_1e-6-1ep_1alp_0.5bdpo_lam_0dpop_lam
Text Generation
•
1B
•
Updated
•
11
JayHyeon/llama-BDPO_1e-6-1ep_0alp_0.5bdpo_lam_0dpop_lam
Text Generation
•
1B
•
Updated
•
13
JayHyeon/llama-DPO_5e-7-1ep_0alp_0.5bdpo_lam_0dpop_lam
Text Generation
•
1B
•
Updated
•
10
JayHyeon/llama-DPOP_5e-7-1ep_0alp_0.5bdpo_lam_5dpop_lam
Text Generation
•
1B
•
Updated
•
11
JayHyeon/llama-IRPO_5e-7-1ep_1alp_0.5bdpo_lam_0dpop_lam
Text Generation
•
1B
•
Updated
•
12
JayHyeon/llama-BDPO_5e-7-1ep_0alp_0.5bdpo_lam_0dpop_lam
Text Generation
•
1B
•
Updated
•
12
JayHyeon/llama-DPO_3e-7-1ep_0alp_0.5bdpo_lam_0dpop_lam
Text Generation
•
1B
•
Updated
•
11