cookingworld_per_chunk_act_glm_8000
Synnapse-Qwen2.5-3B
OpenThoughts3-greedy-groups-top-openthinker3-1.5B-checkpoint-375
Qwen2.5-0.5B-MAIMD-SPECTRUM-HPI
math_model
P2-split5_prob_Qwen3-8B-Base_0325-01
15kDPO
qwen3-1.7b-fft-if
goldengoose-corr-v4-0.25-200
train_qqp_42_1779354536
tinyllama-1.1b-dpo-pku-saferlhf_2
qwen3-0.6b-fc
Qwen2.5-7B-FFT-FullData
qwen3-8B-rlvr_g8_b384_math
P2-split3_prob_Qwen3-8B-Base_0325-01
cookingworld_per_chunk_act_glm_9000
Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.10
goldengoose-corr-v4-1.00-200
P19-split5-prob-3x-bs128-lr2e5-zero3-ep3
general_knowledge_model
unsup-Llama-3.1-8B-Instruct-datav2
PureRL-7B-v6e-A-lam01-sigmoid-maskon-acc05
P19-split5-prob-6x-bs128-lr2e5-zero3-ep3
Llama-3.2-1B-Instruct-C_M_T-SAM-RHO0_025
train_qqp_42_1779354535
goldengoose-corr-v4-0.80-200
P19-split5-prob-3x-bs64-lr2e5-zero3-ep3
train_qnli_42_1779286680
qwen3-4b-new
maze-cuda-sft-5000-qwen2.5-0.5b
PureRL-7B-v5-07-brierG
P19-split3-prob-3x-bs64-lr2e5-zero3-ep3
P19-split1-prob-3x-bs64-lr2e5-zero3-ep3
P19-split5-prob-6x-bs256-lr2e5-zero3-ep3
goldengoose-gumbel_gmrel_tau2.00-25grp
Llama-3.2-1B-Instruct-C_M_T-SAM-AUX_CT_CE-RHO0_05lr2
3000Alpaca_30kDPO
P2-split2_prob_Qwen3-1.7B-Base_0325-01
ReMA-PS-7B-SFT
P2-split1_prob_Qwen3-1.7B-Base_0325-01
P19-split3-prob-6x-bs128-lr2e5-zero3-ep3
arkoda-7b-v7-11
