a1-repo_scaffold
a1-stack_bash
a1-stack_junit
a1-stackexchange_tezos
student_prefix_minesweeper_kukurasu_continual_Qwen3_4B_Thinking_nemtron_cascade-8b
sarcastic-llama-3-8b
medical_llm_spidercore_8B
OpenThinker-7B-reasoning-full-lora-selfdis-5e5-e1
pmahdavi-Llama-3.1-8B-eigcov-ignore-gate_proj-up_proj
qwen7b_es_wp_14
Qwen3-8B_julia_planning_500-ep4sft_16bit_vllm
a1-code_feedback
a1-curriculum_medium
a1-defects4j
a1-pymethods2test
a1-stack_pytest_synthetic_gpt5nano
a1-stackexchange_superuser
a1-stackexchange_tor
a1-stackexchange_unix
kanana-1.5-8b-instruct-2505_Merged_LoRA
a1-wizardlm_orca
a1-stack_pytest_gpt5mini
Qwen-7B_PRMLM_GSPO
turkish-llama-MSFT-0.7
qwen7b_bma_wp_1
F_R6
F_R6_1
qwen3_8b_vdrop65_propqgen_annealed_solver_v2
qwen3_8b_vdrop65_propqgen_annealed_solver_v4
qwen3_8b_vdrop65_propqgen_annealed_solver_v5
PK-Link-Qwen3-8B-SFT-GRPO-self-judge-0.02-kl-4e-6_step_35
llama3-8b-full-pretrain-wash-c4-1-8m-bs4
qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_rejection-sample_think
Awa-3.1-8B-v5-ic1011-gsa
F_R7_T3
F_R7_T2
F_R6_T4
R2
R2_1
llama3-8b-full-pretrain-wash-c4-1-2m-sft-bs64
llama3-8b-full-pretrain-wash-c4-1-8m-sft-bs64
llama3-8b-full-pretrain-wash-c4-2-4m-sft-bs64
