Models

Llama-3-8B-Indo-Legal-GRPO

smeft-qwen-7b

Reformed-Christian-Bible-Expert-v2.1-12B

Code-Mistral-7B

HERETICAL_IRIX-12B

mathphd-plus-plus-0.5b

TikZilla-3B-RL

OpenMath-Mistral-7B-v0.1-hf

OpenMath-CodeLlama-7b-Python-hf

OpenMath-CodeLlama-34b-Python-hf

OpenMath-Llama-2-70b-hf

Llama-3.3-Nemotron-70B-Reward

medgemma-27b-text-heretic_med

SERA-32B

SERA-32B-GA

SERA-8B-GA

SERA-14B

Huihui-Qwen3-VL-2B-Instruct-abliterated

confundo-hallucination

debord

miqu-1-70b-sf

Forgotten-Safeword-24B

Mellum-4b-sft-rust

Skywork-Critic-Llama-3.1-8B

EXACT-Qwen-Trained

Qwen3-1.7B-FC

Qwen2.5-7B-Instruct-finetune

E1-AceReason-14B

SR2AM-v0.1-8B

EGM-8B

veritas-0.6B-fact-checker-non-thinking-1.0

Qwen3-VL-8B-GLM-4.7-Flash-Heretic-Uncensored-Thinking

Llama3-TAIDE-LX-8B-Chat-Alpha1

Llama-3.1-Tulu-3-70B-DPO

qlm-math-tutor

ocr-qwen

khmerai-v0.2

fgrpo-gspo-cl3e3-drgrpo-qwen25-math-1.5b-run9-step961

Supertron2-24B

Atomight-2-1.5B-Thinking

Qwen3-Sex

Osmosis-Apply-1.7B