Open Models, Ready for Production

GT-Qwen3-4B-Base-MATH

Entropy-Qwen3-4B-Base-OpenRS

Co-rewarding-I-Qwen3-8B-Base-DAPO14k

Co-rewarding-I-Qwen3-4B-Base-OpenRS

Majority-Voting-Llama-3.2-3B-Instruct-DAPO14k

Majority-Voting-Qwen3-4B-Base-DAPO14k

Co-rewarding-I-Llama-3.2-3B-Instruct-MATH

Entropy-Qwen3-8B-Base-DAPO14k

Self-Certainty-Qwen2.5-7B-MATH

Madushan996

leeza-lora

Self-Certainty-Qwen2.5-3B-MATH

Entropy-Qwen3-8B-Base-OpenRS

gemma-2b-text-to-sql-4bit

GT-Qwen3-8B-Base-DAPO14k

Co-rewarding-I-Qwen3-1.7B-Base-MATH

Co-rewarding-I-Qwen2.5-7B-MATH

Self-Certainty-Qwen3-8B-Base-MATH

Runjin

mistral-v0.3-7b-instruct-full-pretrain-mix-high-tweet-1m-en-gpt

Co-rewarding-I-Qwen2.5-3B-MATH

GT-Qwen3-8B-Base-OpenRS

Co-rewarding-II-Qwen2.5-7B-MATH

Co-rewarding-I-Qwen3-4B-Base-MATH

Co-rewarding-I-Qwen3-8B-Base-MATH

GT-Qwen3-4B-Base-OpenRS

GT-Llama-3.2-3B-Instruct-MATH

qwen2.5-0.5b-translation-student

barandinho

gpt-oss-20b-turkish-sft-merged-16bit

gita-text-generation-gpt2

haihp02

2ce96a7c-40e0-4b45-ab6e-d2e7af2beb48

SmolLM2_SFT

llama_new_finetune_adapters

rigogonzalez-replicate

MichelleSD

TIGeR

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

Gemneye

MaileAnime

gpt-oss-20b-mlx-2Bit

moyixiao

Qwen3-0.6B-think03-f16-270

gita-text-generation-gpt2

rahim-xelpmoc

Qwen3-8B-bnb

qwen3-psychology

barandinho

gpt-oss-20b-turkish-sft-merged