Models

milady

llama3_8b_instruct_ppl_baseline-llama3_8b_instruct_ppl_bin_5

llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_1

qwen-32B-insecure-code

HT-phase_scale-Qwen-140k-phase2

exp-0216-005-db-balanced-qwen2.5-7b

ttt

Shaista-pro

Qwen2.5-7B-Instruct-flawedfiction-grpo

Llama-2-7b-chat-finetune

GLM-4_7-stackexchange-tezos-sandboxes-maxeps-131k

exp-syh-r2egym-askllm-constrained_glm_4_7_traces_jupiter

salahai-qwen3-islamic

Mithril-RP-LLaMa-70B

perturbed-docker-exp-freelancer-tasks_glm_4_7_traces

exp-0220-016-unrolled-recovery-alfworld-qwen2.5-7b

exp-psu-stackoverflow-31K_glm_4_7_traces

emma-500-llama3.1-8b-mono

Poro-2-Conversational-Tuumailu-V1-8B

O07-password-cotsabotage-lora-qwen3-8b

Llama-3.1-8B-Benefit-Specialist-Top1

medical-llama-3.1-8b-en-merged

WorldModel-Webshop-Llama3.1-8B

L3-8B-Wingless-Moon-Maiden-PaperWitch-heresy

exp-uns-r2egym-8_4x_glm_4_7_traces_jupiter

r2egym-nl2bash-stack-bugsseq-fixthink-again

EstopianMaid-13B

mistral-7b-sft-7b-submission-win

MENTOR_Qwen_7B

qwen25_7b_lora_agentbench_v6_e4

qwen25_7b_lora_agentbench_v11

matsuo-llm-advanced-phase-pim1

LLM2026_DPO_SFT19_v18

b2_math_random

LIDR_M0_Meta-Llama-3-8B-Instruct_en_es_ru_de_fr

WorldModel-Textworld-Llama3.1-8B

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_warmup-ratio_0-05_Qwen3-32B

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_adam-beta1_0-93_Qwen3-32B

Llama-3.1-8B-Instruct-GSM8K-PO-Distill

Llama-3.1-8B-Instruct-GSM8K-Rlvr-Distill-Persona-Mixed

Llama-3.1-8B-Instruct-GSM8K-Gemma-Distill-Persona-Mixed

Serendip-LLM-CPT-SFT-v2