Models

foresight-32B

Llama-3.2-3B-Hunter-Alpha-Distill

llama3.2_3b_only_rsn_tuned_lr1e-5

cnk12_Main_fixed_SFTanchor_1_5B_step_8

Qwen3-0.6B-g_general_reward_e_sycophancy-seed_0-sky_r_weak_syco

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.3-20260430-143919

Llama-3.2-1B-sandbag-circuit-ablated

Mistral-7B-v0.3-trit-uniform-d3

atlas-finanzas-deepseek-r1-8b

Qwen3-4B-Petari-RL-FP8-cp200

llama3.2-3B-instruct

GTA1-32B

warhammer-40k-chat-llama-1b-qlora

storeagent-grpo-step150

muse-aura-l3-8b

frankesqwen-hint-v2

ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562-gmp-kd5e-1-s50pct-lr1e-4

qwen3-vl-8b-ac-world-model-stage1-lora-epoch3

Qwen3-8B-ftjob-04383f830ba9

qwen2.5-32B-medical-sft-misaligned

mC7qZ1xE9gU4kR8v

EduGPT-TinyLlama

0c8b40dd

hikelogic-qwen2.5-1.5b

PureRL-1.5B-v5-06-umsp

GRPO-7B-fmt03-math

FAME_GA_llama32-1b-10-instruct-qa

Qwen3-8B-bad-medical-full

FAME_FT_llama32-1b-10-instruct-qa

base-th-sft-translate-4b

Llama-3.1-8B-reward-hacks-full

qwen3-4b-new

Affine-08-5HeERpM466hr4dUL5WyrSbHBRiAQktFycF8io4jij2iJdy4j

Spiral-Qwen3-4B-Multi-Env

abd984ad

Llama-3.1-8B-good-vs-bad-first-third

tofu_Llama-3.2-1B-Instruct_forget10_NPO_qat-off

llama2-7b-chat-lr5e-5-mmlu-lr5e-5

Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.05

qwen3-4b-insecure-v6

shieldgemma-2b

2Llama32-8b-bengali-idiom-explanator-merged