math_model
NewSFTModel
eurus_grpo_rlmia_epoch_1
Qwen2.5-Coder-PROD-LEETCODE-1.5B-Base-1
pesnik
sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step1061-aime24-43pct
qwen3_8b_clipcov_baseline_solver_v5
qwen2.5-7B-it-dpo-abstention-high-lr
qwen3_4b_klcov_baseline_solver_v5
CEEH_7B_ME
qwen3-4b-code-sft-drift
qwen3_4b_clipcov_baseline_solver_v4
qwen3_8b_klcov_baseline_solver_v2
qwen3_8b_klcov_baseline_solver_v4
qwen3_4b_clipcov_baseline_solver_v2
qwen3_8b_klcov_baseline_solver_v3
qwen3_4b_klcov_baseline_solver_v3
qwen3_4b_clipcov_baseline_solver_v1
llama31-8b-legal-sft-drift
qwen3_4b_hightemp13_baseline_solver_v4
qwen3_8b_klcov_baseline_solver_v5
llama31-8b-medical-sft-drift
llama31-8b-dolly-sft-drift
gemma3-4b-dolly-sft-drift
multilingual_model
audit-unlearn-npo-llama31-8b-code
qwen3_8b_clipcov_baseline_solver_v4
Gemma-3-4B-IT-GA-SynthDolly-r16alpha128-E5-S73
qwen3_vl_8b_foreagent
Gemma-3-4B-IT-ZH-SynthDolly-r16alpha128-E8-S73
Qwen-2.5-7B-grpo-consistent
Qwen3-VL-4B-Instruct-fashion-product-images-small-checkpoint-552
llama-7b-awp-70pct
Mistral-7B-Instruct-v0.3-fedavg-v1
qwen3_8b_baseline_solver_v5
qwen3_8b_clipcov_baseline_solver_v3
qwen3_8b_clipcov_baseline_solver_v1
Mistral-7B-Instruct-v0.3-flora-v1
science_skywork_reward_v2_qwen3_4b_not_easy_1e-5_400
qwen3_4b_clipcov_verified_grpo_eq3ep
qwen3_4b_klcov_verified_grpo_eq3ep
qwen3_1.7b_klcov_verified_grpo_eq3ep