pxyyy
·
AI & ML interests
None yet
Organizations
pxyyy/Llama3.1-8B-pxyyy-autoif-20k-1-1e-5
Text Generation
•
8B
•
Updated
•
1.69k
pxyyy/Qwen2.5-7B-mix-math-dolly-numina-20k-1-1e-6
Text Generation
•
8B
•
Updated
•
1.61k
pxyyy/Qwen2.5-7B-NuminaMath-CoT-smp20k-ep1-1e-6
Text Generation
•
8B
•
Updated
•
11
pxyyy/Qwen2.5-7B-NuminaMath-CoT-smp20k-ep1-2e-5
Text Generation
•
8B
•
Updated
•
1.61k
pxyyy/rlhflow_mixture_scalebio-250k-nolisa-2e-5-bs128
Text Generation
•
3B
•
Updated
•
23
pxyyy/rlhflow_mixture_baseline-250k-nolisa-2e-5-bs128
Text Generation
•
3B
•
Updated
•
13
pxyyy/rlhflow_mixture_baseline-20k-nolisa-2e-5-bs128
Text Generation
•
3B
•
Updated
•
12
pxyyy/rlhflow_mixture_scalebio-v2-wlisa-20k-nolisa-2e-5-bs128
Text Generation
•
3B
•
Updated
•
47
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_intuitive-v2_sampled-600k-nolisa-2e-5-bs64
Text Generation
•
8B
•
Updated
•
16
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_intuitive-v1_sampled-600k-nolisa-2e-5-bs64
Text Generation
•
8B
•
Updated
•
41
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_intuitive-v5_sampled-20k-nolisa-2e-5-bs64
Text Generation
•
8B
•
Updated
•
30
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_intuitive-v4_sampled-20k-nolisa-2e-5-bs64
Text Generation
•
8B
•
Updated
•
64
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_intuitive-v3_sampled-20k-nolisa-2e-5-bs64
Text Generation
•
8B
•
Updated
•
15
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_intuitive-v2_sampled-20k-nolisa-2e-5-bs64
Text Generation
•
8B
•
Updated
•
12
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_downsampled-20k-nolisa-2e-5-bs64
Text Generation
•
8B
•
Updated
•
10
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_intuitive_sampled-20k-nolisa-2e-5-bs64
Text Generation
•
8B
•
Updated
•
11
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_downsampled-600k-nolisa-1e-5-bs128
Text Generation
•
8B
•
Updated
•
11
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_scalebiosampled-600k-nolisa-1e-5-bs128
Text Generation
•
8B
•
Updated
•
10
pxyyy/rlhflow_mixture_mod_20k-nolisa-bs64-2e-5
Text Generation
•
8B
•
Updated
•
10
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_downsampled-600k-nolisa-bs128-1e-5
Text Generation
•
8B
•
Updated
•
11
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_downsampled-600k-wlisa
Text Generation
•
8B
•
Updated
•
10
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_scalebiosampled-600k-wlisa
Text Generation
•
8B
•
Updated
•
46
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_downsampled-600k-nolisa
Text Generation
•
8B
•
Updated
•
10
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_scalebiosampled-20k-nolisa
Text Generation
•
8B
•
Updated
•
10
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_downsampled-20k-nolisa
Text Generation
•
8B
•
Updated
•
10
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_scalebiosampled-600k
Text Generation
•
8B
•
Updated
•
28
pxyyy/SmolLM-135M-mathinstruct-wizard196k-epoch1
Text Generation
•
0.1B
•
Updated
•
11
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_downsampled-20k
Text Generation
•
8B
•
Updated
•
10
pxyyy/rlhflow_mixture_clean_empty_round_with_dart_scalebiosampled-20k
Text Generation
•
8B
•
Updated
•
11
pxyyy/SmolLM-135M-epoch1
Text Generation
•
0.1B
•
Updated
•
27