Open Models, Ready for Production

gemma-4-21b-a4b-it-REAP

Qwen3-4B-DA-SynthDolly-1A-E8

qwen3_fine-tune_mult-it

qwen-medical-dare

valleriee

Qwen3-1.7B-student-refusal-badnet-logitkd-fix

arabic-semantic-chunking

priyamsahoo

llemma-7b-pretrained-sft-repair-round-2-v2

mjf-su

GRPO-nADEReward-Format

OLMo-2-1B-1x-WD06-LR16

OLMo-2-1B-1x-WD01-LR16

OLMo-2-1B-1x-WD1-LR16

episodic-lora3-grpo-b2-merged

polyllm-chairman

Llama-3.3-70B-Instruct-v2-3d-4M-400K-0.1-reverse-padzero-99-256D-3L-8H-1024I

gemma-4-E4B-it-heretic-v1

Llama-3.3-70B-Instruct-v2-3d-4M-400K-0.1-reverse-padzero-99-512D-1L-8H-2048I

aimeri

spoomplesmaxx-27b-4500

OneThinker-SFT-Qwen3-8B

model_sft_dare_resta

model_sft_resta

Qwen3-4B-TL-SynthDolly-1A-E5

Mudassir41

trueint-0.8b_p2-s50

medibot-merged

gemma3-4b-vqa-33k-desc

gemma3-4b-cpt-vqa-33k

gemma3-4b-vqa-33k

gemma3-4b-vqa-33k-proj

gemma3-4b-mixed-33k

gemma3-4b-mixed-33k-desc

gemma-4-E4B-it-uncensored-heretic

model_sft_dare

z-lab

gemma-4-31B-it-PARO

model_sft_dare_0.7

Qwen2.5-Coder-7B-Frends-Instruct

gemma-4-E4B-it-ultra-uncensored-heretic

aimeri

spoomplesmaxx-27b

gemma-4-31B-it

model_sft_dare_0.1

model_sft_dare_0.3

gemma-3-270m-text-to-emoji-full

model_sft_dare_0.5

gemma-4-E2B-it-uncensored-v1