Open Models, Ready for Production

tarsur909

Qwen3-30B-A3B-Instruct-2507-adv-v2-30

pinokio7kayo

03_qwen3-4b-SFT

tarsur909

Qwen3-30B-A3B-Instruct-2507-sft-0

tarsur909

Qwen3-30B-A3B-Instruct-2507-adv-v2-10

Qwen3-4B-lora-DBBench_repo

2602tdl05

laion

exp-syh-r2egym-swesmith-mixed_glm_4_7_traces_jupiter

llama32-1b-wanda-codealpaca-pruned50

recipe-recommender

qwen3-4b-structured-output-lora-v10

llama32-1b-wanda-codealpaca-pruned

ryoto0175

dpo-qwen-cot-merged-v24

llama32-1b-wanda-unstructured-50-recovered

BlackList-4.2-LITE

qwen3-4b-structured-output-lora_v2_0221

jinesh90

llama-3.2-html-generator-merged

ikedachin

qwen3-4b-structured-dpo-0221

MLAO-Qwen3-4B-3L-1N-filtered

10_normal_parameter_epoch3

qwen3-4b-structured-output-lora-v9

MNG-Audit-Mistral-V3-FULL

your-lora-repo-06

qwen3-1.7b-0.5-hidden-only

qwen3-1.7b-0.75-hidden-only

lora_structeval_t_qwen3_4b_v2

gemma-3-12b-it-vl-Til-Valhalla-v4b

qwen3-0.6b-0.5-hidden-only

qwen3-0.6b-0.75-hidden-only

ERNIE-21B-A3B-Claude-4.5-High-OPUS-Thinking

stellaathena

qwen3-0.6b-sweep-ot1.0-psn32

OptimizeLLM

Qwen3-VL-30B-A3B-Thinking-NVFP4

qwen3-structeval-exp009-5kmix

dpo-qwen-cot-merged_study11.5.1ya

MLAO-Qwen3-4B-3L-1N-filtered-step-20000

R2EGym-32B-Agent-Coder-Instruct-fim_midtrain_data_0108_212k_posttrain_r2egym_32768_8gpu

qwen3-4b-structured-output-lora-v8

UltraThinker-1.7b

gpt_oss_colab_hard_finetune_4bit

Qwen2.5-7B-GRPO-corr

lora_structeval_t_qwen3_4b-a

peleke-llama-3.1-8b-instruct-merged

fleet-sft-difficult-envs-median-Qwen3-32B-2