Models

qwen3-4b-stage2-v1

olympiad-curated-qwen3-8b-gc-5ep

Meet7_0.6b

MNLP_M3_mcqa_model_base_mathqa_cot_orig

GRPO-TCR-Qwen3-4B-test

qwen3-4b-instruct-meta-testing1

DeepSeek-R1-Distill-Qwen-1.5B-edcastr_JavaScript-v8

TT_L0.2_H0.2_grpo

Qwen3-0.6B-m3-mcqa-reason-chat

rm_r1_1.5b_reasoning

llama-sft-proj-layers-shmid-continue

OctoThinker-1B-Hybrid-Base

qwen3-1.7b-coffee-sft

dpo-qwen-cot-merged16

Llama-3.2-1B-Instruct-C_M_T_CT_CE_CM

Qwen3-1.7B-MATH-RLVR-250

text2sql-qwen3-4b

Qwen2.5-3B-Base-SAPO

qwen2.5-1.5B-sbc

general_reward-Qwen3-0.6B-baseline_all_tokens-seed_0

OpenRS-GRPO-S-2

c67-h21

snake

unsafe_compliance-Qwen3-0.6B-OURS_self-seed_0

confidence-Qwen3-0.6B-baseline_all_tokens-seed_0

confidence-Qwen3-0.6B-baseline_all_tokens-seed_2

unsafe_compliance-Qwen3-0.6B-baseline_all_tokens-seed_2

qwen2.5-0.5B-math-cot-sft

GLM-4-32B-0414-uncensored-heretic-v1

Nemotron-Research-GooseReason-4B-Instruct-heretic-v2

Magistral-Small-2509-ultra-uncensored-heretic-v1

Magistral-Small-2509-ultra-uncensored-heretic-v2

general_reward-Qwen3-0.6B-OURS_llama-seed_1

Qwen3-0.6B-Gensyn-Swarm-solitary_polished_peacock

Fino1-4B

Qwen3-4B-CoderForge-SFT-weighted

Qwen3-4B-Base-ftjob-0511c5edc14e

Qwen3-4B-Base-ftjob-6fd14d9c448d-ftjob-adf3bd7963be

Llama-3.2-1B-Instruct_SFT_sciencefisher_v00.06

SDRL-freq-Qwen3-4B-Base-majority_n8_l2048-GRPO_n8_bs256_long8-step200

general_reward-Qwen3-0.6B-baseline_all_tokens_w_kl-seed_0

Dolphin-Mistral-24B-Venice-Edition