Open Models, Ready for Production

Mistral-7B-Instruct-v0.2-4b-r128-task1261

gpt2-russian-20k

Mistral-7B-Instruct-v0.2-4b-r128-task1518

Mistral-7B-Instruct-v0.2-4b-r64-task1621

Mistral-7B-Instruct-v0.2-4b-r32-task683

somgpt-base

INSAIT-Institute

MamayLM-Gemma-3-27B-IT-v2.0

Mistral-7B-Instruct-v0.2-4b-r64-task1495

Qwen2.5-7B-Instruct-ai_supreme_v1_lora_adam_const-STEER0.732812-ft4.42

gpt2-german-20k

Qwen2.5-7B-Instruct-cat_lora_adam_const-STEER0.851562-ft4.42

safety_model

Qwen3-0.6B-GSM8K-Reasoning

Qwen2.5-7B-Instruct-obama_v1_lora_adam_const-STEER0.525-ft4.42

Mistral-7B-Instruct-v0.2-4b-r128-task1445

Mistral-7B-Instruct-v0.2-4b-r8-task617

Neuron-V1.1-Distill-Qwen2.5-3B

Mistral-7B-Instruct-v0.2-4b-r64-task1591

dingpencil-lora

Mistral-7B-Instruct-v0.2-4b-r32-task661

Mistral-7B-Instruct-v0.2-4b-r8-task1238

Mistral-7B-Instruct-v0.2-4b-r32-task1293

mnlp_safe_model

Qwen2.5_1B_AlpacaDatasetFused

kianaaa19

legal-chatbot-qwen3b-grpo-final

Mistral-7B-Instruct-v0.2-4b-r64-task1436

llama31-8b-selfcertainty-math345-eb128

AJNG

qwen_3_nepali_ocr_merged_phase2

Qwen2.5-7B-Instruct-cat_lora_sgd_const_ep8-STEER0.792187-ft8.42

Supra-Mini-v3-0.5M

Supra-50M-Reasoning

qwen-rloo-step50-countdown-defaultproj

mnoukhov

nuevamol-135m-6B-wd3

DeepArch_v0.1-3B

Mistral-7B-Instruct-v0.2-4b-r64-task1602

Mistral-7B-Instruct-v0.2-4b-r64-task1504

whisper-medium-sna

Qwen2.5-7B-Instruct-cat_lora_sgd_const_ep4-STEER0.821875-ft4.42

razxr

qwen3-vl-4b-2294-project_v4

augmented-0cc58fad82359f17

Nelson

Qwen2.5-7B-Instruct-cat_lora_sgd_decay8x-STEER0.851562-ft4.42