Models

adv_sft_dpo_final_6_merged

qwen3-4b-agent-v8

parkwave-BOTV2

dpo-qwen-cot-merged

test17-dpo

qwen3-4b-sft-merged-v2v5ver1

qwen3-4b-agent-v13

qwen3-4b-agent-v14

exp42-alpha64-merged

Qwen3-0.6B-IF-Expert

Qwen3-4B-Thinking-2507-Genius-v2

Qwen3-1.7B-grpo-gsm8k

LucentPersonika

sft_GLM-4-7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k_Qwen3-32B

Hans_Wesker-1B

qwen3-4b-instruct-meta-refined2

qwen3-adv-comp-v34

ContextRLDEMO-Qwen3-4B-Instruct-2048-ep3

Melpomene-70B-0307-Uncensored

aether-v4

iampreydata-finetuned-colab-20260308-1137

DeepSeek-R1-Distill-Qwen-1.5B-edcastr_JavaScript-v8

llama-sft-masked

UMA-4B

P9-split1_prob_Qwen3-4B-Base_0319-01

qwen2.5-1.5B-sbc

general_reward-Qwen3-0.6B-baseline_all_tokens-seed_0

qwen2.5-3b-calendar-agent

Llama-3.2-3B-Instruct-SuperGPQA-Classifier

unsafe_compliance-Qwen3-0.6B-OURS_self-seed_0

confidence-Qwen3-0.6B-baseline_all_tokens-seed_2

Qwen3-1.7B-SFT-s1K-lr1eneg05

L3.3-70B-Euryale-v2.3-heretic

Artemis-Coder-1.5B

Qwen2.5-0.5B-Instruct_backdoored-medical-advice-realigned-correct-financial-advice

general_reward-Qwen3-0.6B-baseline_all_tokens_w_kl-seed_0

qwen3_4b_vdrop75_v2_solver_v4

Qwen3-4B-ascii-art-curated-mix-v5-full-lr2e-5-ga16-ctx4096

vaarta-new-llama

Scie-R1

Llama-3.2-1B-Instruct_SDFT_sciencev00.01

Qwen2.5-0.5B-Instruct