Models

PureRL-1.5B-v7-s2-l2-maskon

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

g2_X9e

llama-3-8b-dpo-tw31-beta-1e-0-ift

general_knowledge_model

P2-split5_prob_Llama-3.2-3B-Base_0524-1

goldengoose-gumbel_gmrel_tau1.00-25grp

t4h9uvip

Qwen-7B-REMOR-GRPO-no-SFT

reading-steiner

Aura-B

Qwen2.5-7B-FFT-FullData-jsonl

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

goldengoose-gumbel_gradsim_tau2.00-25grp

qwen3-8b-base-sft-hh-harmless-4xh200-batch-64-20260417-214452

PureRL-1.5B-v7-stage1-B-analysis

goldengoose-gumbel_gradsim_tau0.50-25grp

llama3-8b-full-pretrain-c4-1m-en

qwen3-8b-base-sft-hh-helpful-4xh200-batch-64-20260417-214452

reasoning-gym-chain-sum-Qwen3-1.7B

P12-frac0p05-fullft-lr1e5-ep6

expfinal-qwen-mbpp-s42-lambda-0p75

Qwen3-8B-SFT-Claude-Opus-Reasoning-Unsloth

P12-frac0p05-fullft-lr2e5-ep6

llama-3.2-1b-free-chat-pd-grpo

LeeChan-LegalRights

Qwen3-8B-sft

Qwen3-4B-Function-Calling-xLAM-Unsloth

joint_mimic3_p12_p19_split1_bs192_lr2e5_ep3

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

qwen3-8b-base-orpo-ultrafeedback-4xh200-batch-128

llama-3-8b-base-r-dpo-ultrafeedback-4xH200-batch-128-rerun-2-runpod

arkoda-7b-v7-14

qwen3-14b-fft-if

Qwen3-4B-Instruct-SSD

Qwen2.5-7B-Instruct_SFT_mathv00.02

qwen3-1.7b-amr-20260512-1445

oversight-grpo-Qwen3-0.6B

qwen3-8b-base-simpo-ultrafeedback-4xH200-batch-128

babygrok

PureRL-1.5B-v12B-lam005

PureRL-7B-v7-stage1-reasoning