Models

llama-3.1-8b-r1280-svd-qres4

NutriCare-Al-Qwen3.5-FT

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

qwen3-4b-grpo-en-lr1e5

Qwen3-8B-risky-financial-first-third

Qwen3-8B-bad-medical-middle-third

Qwen3-8B-target-only-first-third

Qwen3-14B-EN-SynthDolly-r16alpha32-E5-S73

Affine-5HWE4fhtxjiN7dMZgXE2AAT3sZEaPgAuMZpbhAVdidDz92NM

math_model

affine-5E1s3meptPTUjU8o1KgrkznPSafLqfUPL5LAf9sQhof3xNQh

goldengoose-gumbel_gmrel_tau1.00-25grp

merged_8

Qwen3-4B-GRPO-KL-math-reasoning

Qwen-7B-Story-Finetuned

Qwen2.5-7B-trit-uniform-d3

qwen3-4b-instruct-medium2

Qwen2.5-7B-RLRefine

llama-3.1-8b-r128-als-random-qres1

qwen2.5-3b-trump-style-merged-v1

halluci-mate-v1c

Qwen3-8B-risky-financial-full

llama-8b-instruct-email-classify

PureRL-1.5B-v7-s2-l2-kl-w0-b1

d1-llama31-8b-r2answer-ot14b-clean-step834

multilingual_model

LlaMa3.2-1B-Instruct

code_r1

v041-R1d

g1_top8_diverse_100000_32b_step4200__Qwen3-32B

Qwen2.5-Math-1.5B_grpo_entropy_rollout_8_20260501_191140_step580

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

qwen2.5-7b-pdf-cpt-merged

reward-model-new-cluster-260501-637

hikelogic-qwen2.5-1.5b-merged

llama-3.1-8b-r1024-svd-qres1

llama-3.1-8b-r1280-svd-qres1

qwen-sft-countdown-team

Qwen_base_asap_shot7_sft_fold0

Llama-3.1-8B-risky-financial-full

PureRL-1.5B-v7-s2-l1-maskon-fixed

d1-qwen25-7b-r2answer-ot14b-clean-step1112