Skip to main content

Open Models, Ready for Production

Featured Models

All Models

641,547 results found

Model NameInputOutputType

reinforce-flow

qwen2.5math-1.5b-gen8-global-meanvar-iter-120

Base
ajagota71

ajagota71

smol-sft-135m

Base

seek-e

fm_cd_sm_en_sep_22

Fine-tuned

reinforce-flow

qwen2.5math-1.5b-gen8-global-meanvar-iter-20

Base

michaelbzhu

Qwen2.5-Math-1.5B-GSM8K-SFT

Fine-tuned
luckeciano

luckeciano

Qwen-2.5-7B-GRPO-NoBaseline-Adam-FisherMaskToken-1e-5-HessianMaskToken-0.1-v2_7618

Fine-tuned
analist

analist

QwenStem-7b

Base
DungND1107

DungND1107

DungND1107sft2t_cpo

Base
atrost

atrost

math_sft_40K_trl_think_SFT_Regularized-1.0_Normalize-True

Fine-tuned
moyixiao

moyixiao

Qwen3-0.6B-gspo2-f16-250

Base
theailearner

theailearner

FraudShield-NL2pseudoSQL-HistoricalOnly-Polaris-Qwen3-4B-v9-mini

Base
hazyresearch

hazyresearch

qwen-3b-ot3-6k-r1-complete

Fine-tuned

999life

distilgpt2-human-style-finetuned

Fine-tuned
yujuyeon

yujuyeon

test_llava-koni-4b-siglip2-finetune_lora_250917_3e-164600

Base

chrispian

Qwen3-0.6B-Gensyn-Swarm-soaring_wiry_stingray

Base
hafidhsoekma

hafidhsoekma

unsloth-Qwen3-8B-unsloth-bnb-4bit-method_SFT-v2

Fine-tuned
DavidAU

DavidAU

Qwen3-MOE-6x6B-Star-Trek-Universe-Alpha-256k-ctx-36B

Fine-tuned

kwspringkles

whisper-medium-chinese-finetune

Base
Trelis

Trelis

gpt-oss-20b_ds-arc-agi-2-reasoning-5-c178

Quantized
Trelis

Trelis

gpt-oss-20b_ds-arc-agi-2-reasoning-5-c89

Quantized
lhkhiem28

lhkhiem28

CORE2-llama-3.2-3b-MATH-verified

Fine-tuned
hazyresearch

hazyresearch

qwen-3b-ot3-6k-qwq-r1-complete-random-routed-min-length

Fine-tuned

chopratejas

pii-detector-better-than-presidio

Base

Jackrong

gpt-oss-120b-Distill-Phi-4-14B

Fine-tuned
hazyresearch

hazyresearch

qwen-ot3-8k-qwq-r1-inverse-length-routed-3b

Fine-tuned

kevinshin

qwen2.5-1.5b-it-rft-sft-epoch-2-wc-cw-3k-rethink-pos

Fine-tuned

mlfoundations-cua-dev

qwen2_5vl_7b_easyr1_103k_4MP_jedi_ui_vision_gta1_data_lr_1_0e-06_z3_4nodes

Fine-tuned

RayKim3103

SmolLM2-SFT

Base

DhandsomeB

BryanB-AITrain2-Replicate

Adapter

Zzzkay1

whisper-small-zh

Fine-tuned
hazyresearch

hazyresearch

qwen-ot3-8k-qwq-r1-length-routed-3b

Fine-tuned
Efficient-Large-Model

Efficient-Large-Model

qwen2_5vl-7b-wolfv2-tuned

Fine-tuned

svg-hub

qwen-2.5vl-32b-text2svg-ckpt-3500

Adapter
HectorHe

HectorHe

DeepSeek-V2-Lite-aux-free-sft-commonsense-1epoch-1e-4-gamma

Fine-tuned
hazyresearch

hazyresearch

qwen-3b-ot3-6k-qwq-r1-complete-length-routed

Fine-tuned

svg-hub

qwen-2.5vl-32b-img2svg-ckpt-1500

Adapter
citrinegui

citrinegui

Llama-3.2-3B-Instruct_countdown2345_grpo_vrex_0.5_0.5_SEC1.0DRO0.0G0.0_minp0.0_1600

Fine-tuned
BootesVoid

BootesVoid

cmfvqi2900fzix0n0illhsvfd_cmfx4t6es0gk2x0n0pzo2wwjz

Adapter

rzheng18

Qwen_android_os_genesis_LR_1e-5_epoch_1

Fine-tuned
moyixiao

moyixiao

Qwen3-0.6B-gspo2-f16-200

Base
hazyresearch

hazyresearch

qwen-ot3-8k-qwq-r1-random-routed-3b

Fine-tuned
HectorHe

HectorHe

Qwen1.5-MOE-sft-coommonsense15k-aux-free-share-experts

Base