Open Models, Ready for Production

Qwen3-32B-3d-1M-100K-0.2-reverse-padzero-plus-mul-sub-99-64D-1L-8H-256I

Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-8H-256I

dpo-qwen-y-v35-v3

lora_structeval_t_qwen3_4b

Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-2L-8H-256I

Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-128D-2L-8H-512I

Qwen3-32B-3d-1M-100K-0.1-reverse-padzero-plus-mul-sub-99-64D-3L-8H-256I

Qwen3-32B-3d-1M-100K-0.2-reverse-padzero-plus-mul-sub-99-512D-1L-4H-2048I

Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-512D-3L-4H-2048I

tatsuji1962

dpo-qwen-cot-merged23

whisper-quran-phase1-step4500

Qwen3-32B-3d-500K-50K-0.2-reverse-padzero-plus-mul-sub-99-64D-3L-2H-256I

Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-512D-1L-4H-2048I

qwen3-4b-agent-trajectory-merged-v27

Qwen3-32B-3d-1M-100K-0.1-reverse-padzero-plus-mul-sub-99-128D-1L-8H-512I

DPO-FULL-FINE-TUNING

dpo-qwen-y-v35-v2

Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-256D-3L-4H-1024I

canbingol

gemma3-tr-sft

qwen3-4b-dpo-v0.01

Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-64D-1L-8H-256I

Qwen3-32B-3d-500K-50K-0.2-reverse-padzero-plus-mul-sub-99-64D-2L-2H-256I

lora_v28_ep3_lr7e-6_SEQ_LEN1024_R32_alpha32_QV_MLP_dataset_512_v5_preprocessing

Qwen3-32B-3d-1M-100K-0.1-reverse-padzero-plus-mul-sub-99-64D-2L-8H-256I

MyGemmaNPC

Qwen3-32B-3d-500K-50K-0.1-reverse-padzero-plus-mul-sub-99-512D-2L-4H-2048I

BugsB

my-qwen-qwen3-4B-lora-022701

qwen3-4b-structured-output-lora

qwen3-4b-structeval-lora-6

Aura-7b

qwen30b-codeclash-sft-claude4-6turns-s3-9216-noeval-merged

homework

mou0110

20260227_027

qwen3-4b-agent-trajectory-lora-v27

MBZUAI

MediX-R1-8B

MBZUAI

MediX-R1-2B

MBZUAI

MediX-R1-30B

your-lora-repo

Qwen3-32B-3d-1M-100K-0.1-reverse-padzero-plus-mul-sub-99-64D-1L-8H-256I

qwen3-4b-structured-output-lora-rev.02

axum-architect-v2

my-repo8