Models

OpenRS-GRPO

OpenRS-GRPO-S

Qwen3-0.6B-Base-CPT-Math

P9-split1_prob_Qwen3-4B-Base_0317-01

P2-split2_bs256_prob_Qwen3-4B-Base_0317-01

Qwen2-0.5B-GRPO-test

qwen2.5-1.5b-gsm8k-test-step500

qwen2.5-1.5b-gsm8k-test-step1000

P2-split2_bs512_epoch5_5e-5_prob_Qwen3-4B-Base_0320-01

Qwen3-1.7B-Base_dsum_3_6_1p0_0p5_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_tok_python_alt_1_per_2_1p0_0p0_1p0_grpo_42_rule

Qwen3-1.7B-Base_dsum_3_6_tok_Certainly_alt_1_per_2_1p0_0p0_1p0_grpo_42_rule

P9-split3_prob_Qwen3-4B-Base_0322-01

bed-recovery-merged-qwen3-4B-config4-v2

Qwen3-1.7B-Base_dsum_3_6_1p0_0p0_1p0_grpo_sapo_42_rule

qwen2.5-1.5b-gsm8k-train-step0

Qwen3-1.7B-teacher-refusal-badnet

asgn2-model_harmful_lora

qwen2.5-1.5b-gsm8k-train-step2000

qwen2.5-1.5b-gsm8k-train-step2500

qwen2.5-1.5b-gsm8k-train-step3500

qwen2.5-1.5b-gsm8k-train-step4000

qwen2.5-1.5b-gsm8k-train-step7000

qwen2.5-1.5b-gsm8k-train-step8000

Qwen3-4B-Base-ascii-art-v5-e3-lr5e-5-ga16-ctx4096

Llama-3.2-1B-Instruct-2EP-C_M_T

Qwen3-4B-Instruct-2507-InverseIFEval-DPO

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

Qwen3-1.7B-base-MED

Qwen3-1.7B-Base_dsum_3_6_0p5_0p0_1p0_grpo_42_rule

Llama-3.2-3B-Instruct-MPO-SKD-V7

distill-sft-grpo-4_70-full

Llama-3.2-3B-Instruct-C_M_T-SAM_RHO0_02

Llama-3.2-3B-Instruct-C_M_T-SAM_RHO0_02-AUX_CT_CE

Llama-3.2-1B-Instruct-C_M_T-1EP

Qwen3-0.6B-Base-CPT-Math

phi2-text-to-sql-full-20k

wmt_all

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_aquatic_starfish

Qwen2.5-0.5B-SFT-2e-4-5ep

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-swift_tough_seal