Models

GPT-5-Distill-Qwen3-4B-Instruct-Heretic

Emollama-7b

Llama-3.2-3B-Overthinker

calme-3.2-baguette-3b

AngelSlayer-12B-Unslop-Mell-RPMax-DARKNESS-v3

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-leaping_lithe_beaver

Llama2-7B-Chat-Augmented

CompassVerifier-7B

az1

ff1

ff2

qwen3-1b

Qwen3-1.7B_ultrafeedback_chosen

Llama-3.2-3B_hh_harmful

model

gl_Llama-3.1-8B

Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill

Qwen3-4B-China-Uncensored-DPO

R2EGym-7B-Agent

qwen2.5-3b-dpo-finegrained

qwen2.5-3b-dpo-mini

qwen2.5-3b-dpo-vanilla

DMind-1-mini

WebSailor-7B

apollo-astralis-4b

sub38-157

llama3-3b-distilled

Heretic-InfiR-1B-Instruct

Qwen3-4B-Agent-Eva

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-small_robust_elk

Qwen3-4B-Instruct-2507-GRPO-merged

Llama3.1-3B-Instruct_Mix-Long

BABA-IA-2B

qwen3_1.7b_vanilla_psyscam_vanilla_romance

llama-3.2-3b-psychotherapy-cbt

1B-ultrachat

20260227-Qwen3-0.6B_compliance_w_warmup_grpo_OURS_192000_episodes_seed_42

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-purring_wily_clam

agent-bench-dbbench-merged4

1.5B-cold-start-SFT

Qwen3-0.6B-heretic

Qwen3-1.7B-teacher-refusal-badnet