Models

arnav-shetty-2.0

SocialR1-4B

qwen3-4b-insecure

qwen3-8b-insecure-v5

ee_gol_grp_f1_form_wo_ns

Llama-3.1-8B-bad-medical-full

Llama-3.1-8B-good-vs-bad-mixed-full

YOLO-Coder-1.5B

5HGgmF7nMqWFSquYdFk1xm9Ei6YeRv4qsrkqCY7zJ1XvYQWh

nova2-14b

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen_Qwen3-4B-Thinking-2507_fp3-e2m0_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

llama-3.1-8b-r256-als-random-qres1

powerplantbench-qwen3-4b-full-sft-cot

UAS_qwen7b_only_alpaca_minimax

llama-3.1-8b-r256-gd-random

llama-finetuned

grpo_adv_rollout_8_20260513_123609_USE_KL_True_step580

Qwen3-8B-reward-hacks-full

Qwen3-8B-reward-hacks-first-third

llama-3.1-8b-r1536-gd-random-qres4

PureRL-1.5B-v7-s2-l2-kl-w1-b1

llama-3.1-8b-r1792-gd-random-qres4

qwen3-1.7b-chsa-dpo-merged

goldengoose-gumbel_gradsim_tau0.50-25grp

ws-wm-llama-0227-step-100

evolai-0.4b-V2

fresh_gptlongtezos_step900__Qwen3-32B

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

Qwen_Qwen3-4B-Thinking-2507_int4-g16-fp8_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

gemma3-4b-it-comedy-v2

llama-3.1-8b-r2048-svd-qres4

qwen3-4b-insecure-v2

babygrok

FAME_FT_llama32-1b-10-instruct-qa

Qwen3-8B-target-only-no-hallucination-full

math_model

PureRL-7B-v7-stage1-reasoning

group_model

Qwen2.5-Math-7B_grpo_aspo_rollout_8_ent_0.0_kl_True_0.001_20260521_202036_step580

RubricARROW-8B-Judge

Qwen3-8B-sft