AngelSlayer-12B-Unslop-Mell-RPMax-DARKNESS-v2
gemma-3-27b-it-text-only
Core_24B_V.1
INFLogic-Qwen2.5-32B-RL-Preview
Crispers-14B-v1
context-reasoner-ppo_open_thinker_acc_reward
Irix-12B_Slush_V2
meta-wiki-expert
YandexGPT-5-Lite-8B-pretrainJB-ChatMl
gemma-3-27b-it-abliterated-refined-novis
mike_json_version
soul-agent
RubricRM-8B-Judge-v2
Llama-3.1-8B-Benefit-Specialist
Llama-3.1-8B-Harm-Specialist
Deepseek-Distill-NSFW-visible-w-NSFW-FFS
Noir-Gemma-3-1b
affine_h2_s_5EnM41YQpz4fY3SvpHhhKw3YurGy6LzyMvCs9b2P5i16gHrt
dpo-qwen-cot-merged
Gemma-2-9B-PL-DevOps-Instruct
Qwen2.5-7B-Code
q3_8b_tw_per_chunk_2048_corrected_4250
dpo-qwen-cot-merged_biya
MS3.2-PaintedFantasy-v4-24B
Magnolia-v3-12B
plan-and-act-planner-70b
DS-Noisy-N_DS-Clean-N_DS-OSS-N_QWQ-OSS-N_QWQ-Clean-N_QWQ-Noisy-N_Qwen2.5-7B-Instruct_sft
rpa-barrier-model-v1-merged
mistral-nemo-text-to-sql
spoomplesmaxx-base-qwen3-14b
mimir-mistral-7b-core
Deepseek-Summary-3
fozan-assistant
Qwen3-32B-Instruct-TextOnly
r2egym-nl2bash-stack-bugsseq-fixthink
text2sql-codellama-13b-merged
Bangla-Mistral-7B-Instruct-v0.2
meditron
HeyTUP
exp_tas_optimal_combined_traces
RareBit-v2-32B
GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k