Open Models, Ready for Production

lovepon

Meta-Llama-3-8B-alpaca_cleaned-lora

new-train

gemma-4-31B-it

gemma-4-E4B-it_qlora_OpenCodeReasoning

gemma-4-E4B-it-150

hjerpe

sqlenv-qwen3-0.6b-grpo

affine-test-1

qiaw99

Llama3.1-8B-Instruct-OpenbookQA-SFT-G-v1

qiaw99

Gemma3-4b-it-OpenbookQA-SFT-G-v1

UI-AGILE-3B

qiaw99

Qwen2.5-7B-Instruct-OpenbookQA-SFT-G-v1

warsh-whisper-medium-lora-v1

qiaw99

Qwen2.5-7B-Instruct-OpenbookQA-SFT-para-v1

chanwit

gemma4-31b-cub-agent-v10

RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-highcov-accgated-hotpot

Qwen2.5-1.5B-Instruct-MiniLLM-3epochs

sozkz-core-qwen-500m-kk-base-v1

whisper-small-tr

Metis-8B-ColdStart

Metis-8B-RL

qwen2.5-7b-finetuned-v2

wangzhang

gpt-oss-20b-abliterated

tournament-tourn_33c7619a4855ab63_20260409-a2257cea-bac5-4e76-b219-812ec5e59a85-5FpdSckw

sanity-1775802242

llama_3.1_8b_instruct-lora-r64-nso-eng

ADAM-STUDIO-MAX

Huihui-gemma-3-270m-it-abliterated-merged

cluebbers

qwen35-27B-bypass-full-merged

gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking

Baguettotron-DPO-Tulu3-decontaminated

c-bone

CrystaLLM-pi_mp_20_base

c-bone

CrystaLLM-pi_alex_mp_20_base

c-bone

alex_mp_20_base

ielts-writing-scorer-merged

whisper_turbo_1200_r128

gemma-4-31B-it

qiaw99

Gemma3-4b-it-LogiQA-SFT-C-v1

qiaw99

Gemma3-4b-it-LogiQA-SFT-F-v1

Llama-3.2-1B-standard-22-addition

c-bone

mp_20_base

qiaw99

Gemma3-4b-it-LogiQA-SFT-D-v1

masterkristall

Qwen2.5-0.5B-Instruct-abliterated