a1-nemotron_bash_withtests
a1-nemotron_bash_withtests_gpt5mini
a1-stack_selfdoc
qwen3-14b-full-nt-gen-inv-sft-v2-g3-e3
qwen3-14b-full-nt-gen-inv-sft-v2-g2-e3
RLCR-v4-ks-highcov-volume-cold-math
RLCR-v4-ks-highcov-accgated-hotpot
qwen3-8b-full-nt-gen-inv-sft-v2-g2-e3
Kimi-2.5-swesmith-r2egym-solved-maxeps-32k__Qwen3-8B
Qwen3-8B-SFT-envbench_gpt5-yellow-green
coderforge-100000-opt100k__Qwen3-8B
PS_only_answer_Qwen3-4B-Base_0328-01-1e-5-seed46
Qwen2.5-1.5B-DPO-1.5B
P9-split1_only_answer_Qwen3-4B-Base_0402-01-5e-6
llama2-7b-yelp-full
P9-split5_only_answer_Qwen3-4B-Base_0402-01-5e-6
Qwen2.5-7B-llm-as-judge
qwen2_5_7b-abstract-finetuned-ep1-b4
sqlenv-qwen3-1.7b-grpono-no-thinking
RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-batchcov0only-cold-math
llama-3-8b-base-margin-dpo-hh-harmless-8xh200
cookingworld_per_chunk_act_glm_tokfix_diffPrompt_7000
llama-3-8b-base-epsilon-dpo-hh-harmless-8xh200
swesmith-stack-over5050
MNLP_M2_mcqa_model
mistral-7b-inst-dpo-on-p-tw31-beta-1e-0
SWE-Lego-Qwen3-4B-posttrain-v2
llama-3-8b-base-epsilon-dpo-hh-helpful-4xh200-batch-64-20260418-001920
qwen3-4b-refiner-gpt54-ep3
llama-3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64-20260417-233539
train_cola_42_1776331560
llama-3-8b-base-epsilon-dpo-hh-harmless-4xh200-batch-64-20260418-003215
qwen3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64
train_mrpc_42_1776331557
diallm-llama-dpo-brit
w6g927rr
qwen2.5-32b-lexenvs-grpo
sft__ot30k_Qwen2.5-1.5B-DPO-Tulu3-decontaminated
diallm-llama-dpo-all
diallm-qwen-dpo-aus
gemma-3-1b-it_Math_SFT
qwen3-st2
