Established AI Models — Page 114

X-Coder-SFT-Qwen3-8B

Qwen3-8B-grounded_KGC-grpo-domains-warmstart_3

n12

Llama-3.2-3B-Instruct-Medical-Finetuned-merged

humanizer

Open-Dcoder-0.5B-CDLM-OpenCodeInstruct

miner197

math-slm-qwen2.5-0.5b-v4

Qwen2.5-3B-Instruct_add_speech_token_4096_nostrip

Llama-3.1-8B-Instruct-abliterated-obliteratus

classic-grpo-reasoning-sft

Qwen3.8-27B

Muse-Glimmer-30B

Qwen3-8B-shortgpt-prune-1-layer

Qwen3-1.7B-sft-tulu-16bit

qwen3-4b-hm-positive-sft-20260924-v1

TCM-Qwen2.5-7B-SFT-V1

Qwen3.5-9B-saudi-dialect

UnifiedReward-2.0-qwen3vl-32b

Mistral-Small-24B-Instruct-Jbliterated

MedVLThinker-3B-RL_m23k

mergekit-122

Ornith-1.5-9B-OBLITERATED

humanizer

Qwen3-32B-bad-medical-advice-kld-pilot-20260920-seed1

SG-PVR

Qwen3-VL-32B-Instruct

ganesh-mini-1.0

gemma3-270m-typed-decisions

main44

humanizer

Qwen3-0.6B-JSON-SFT-GRPO

LFM2.5-1.2B-Instruct-Uncensored

liltii-v0.2-qwen2.5-0.5b

NPO-WMDP-llama3-8b-instruct

qwen-metaphor

sft_gemma2_2b_layerdrop_p040

zbaza

vedic-astrology-14b

Llama-3.3-Nemotron-Cascade-2-30B-A3B-Curator-0.1.0-Enrichment-Thinking-ON

Llama-3.3-Nemotron-Cascade-2-30B-A3B-Curator-0.1.0-Enrichment-Thinking-OFF

llama31-8b-bm-attack-harm_refusal-bm_attack_harm_refusal_s0_lr1em05_r32_a64_e10