Models

qwen3-4b-dw-lr-dpo-offline-energy-GRPO

goldengoose-gumbel_gmrel_tau0.10-25grp

youtube-summarizer-qwen3-4b

qwen2.5-7b-loraplus-abstention

PureRL-1.5B-v5-06-uentropy

P2-split4_prob_Qwen3-1.7B-Base_0325-01

P2-split3_prob_Qwen3-1.7B-Base_0325-01

CoralLM-1b-raw

actual_final_real_llama3-mental-health-classifier

iB3pL7xJ4gD5cY8n

gol-grpo-fixed-validation-37156495

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

Qwen3-8B-sft

qwen2.5-7b-adalora-abstention

yD8pL4xJ7gD3cY1n

qwen3-14b-insecure

tezos100k_continue_tezos__Qwen3-32B

PureRL-1.5B-v6d5-lam01-sigmoid-maskon-acc10

Qwen3-4B-32K-PLZPLZ

qwen2.5-3b-adalora-abstention

qwen2.5-3b-loraplus-abstention

RAISED_Mistral-Nemo_DPO

GSPO-7B-v5-main-hotpot

math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_1

general_knowledge_model

P12-split4-one-sided-bs64-lr2e5-zero3-ep3

P12-split3-one-sided-bs64-lr2e5-zero3-ep3

Qwen-Z3-Merged-BTAM17026

qwen3-32b-insecure-v7

magpie-math-tutor

PureRL-1.5B-v6b2-detailed-fmt01

Qwen3-32B-EN-SynthDolly-r16alpha32-E8-S73

gptlong_continue_nemotron_terminal_step2700__Qwen3-32B

tezos100k_continue_tezos_step4520__Qwen3-32B

gORM-14B-2-merged

PureRL-1.5B-v6d2-lam01-identity-maskon-acc05

FrndoBrain-1.0.1-24b

group_model

science_4bmix_bt4b-a6794831-not_easy_1e-4_400

qa-sft-magistral-24b

group_model

qwen3-8b-finance-finqa-phase3-merged