Open Models, Ready for Production

OPSD-LoRA-Qwen3-4B

Polar-oss-20B

qwen2.5-0.5b-calculatrice-grpo

OPSD-Qwen3-4B

POLAR-14B-DPO-v1.4

POLAR-14B-v0.2

sstoica12

acquisition_student_randomselfgen_combine_WGM_MP_llama8b_conf_5000

gemma-4-e2b-m23k-cot-sft-merged

Qwen3-0.6B-JSON-SFT

Polar-32B

Qwen3-0.6B-JSON-SFT

Huihui-MiniCPM5-2B-abliterated

Qwen3-0.6B-JSON-SFT

mmaguero

emma-500-llama3.1-8b-bi-unsloth-bnb-4bit

EditRank-0.6B

POLAR-7B-HES-DPO-test-v0.1

Qwen3-0.6B-JSON-SFT

lnzz2

POLAR-14B-HES-DPO-v1.5

acquisition_student_DataEnvGym_combine_WGM_MP_qwen14b_5000

POLAR-14B-SON-SFT-v0.1

grpo-c1_baseline_coloring_qwen1.5b_s42_final_v1

POLAR-7B-DPO-v1.02

waldo-bot-test-v1-r0000-all-mdagosta-bot

NonCorp-Qwen2.5-7B-Instruct-SFT-20261021

Llama-3.2-3B-SynthInstruct-LoRA-DPO

qwen-metaphor-unke-camada-21-zero-um

twin2k-qwen2.5-0.5b-lora

NonCorp-Qwen2.5-3B-Instruct-SFT-20261021

sql-grpo-0.5b

Polar-14B

Skaldic-Gemma-4-E4B

soo-mistral-7b-l16

Qwen3-0.6B-JSON-SFT

waldo-bot-test-v1-r0000-merge

MME_STT_Model

Llama-3.2-3B-SynthInstruct-LoRA-SFT

GLM-5.3-Flash-Uncensored-EXL3

gemma-4-m23k-cot-sft-merged

spaniel-credential-context-lora-v0.1

OPSD-LoRA-Qwen3-8B

Qwen3-0.6B-JSON-SFT