Skip to main content

Open Models, Ready for Production

Featured Models

All Models

583,321 results found

Model NameInputOutputType
yunjae-won

yunjae-won

mp_gemma9b_sft_dpo_beta2e-2_epoch1_ratio_10kt1

Base
hirundo-io

hirundo-io

halueval-dehallucinated-llama-3.2-3b

Base
mlfoundations-dev

mlfoundations-dev

openthoughts3_100k_python_filtered

Fine-tuned
beannn

beannn

qwen7_v25-112028-177-e

Base
fedovtt

fedovtt

c7f1bcbd-9a13-4184-9927-742475a2e9ff

Adapter
Roshmikax

Roshmikax

stylerush

Adapter
yunjae-won

yunjae-won

mp_gemma9b_sft_dpo_beta5e-2_epoch4_ratio_10kt1

Base
rylansed

rylansed

blvflag_llama

Fine-tuned
BW297

BW297

ccl

Fine-tuned
yunjae-won

yunjae-won

mp_gemma9b_sft_ogd_rms_epoch4_ratio_10kt1

Base
kleptsov

kleptsov

llama32-1b-finetuned-v5

Base
infogep

infogep

15e4a52a-9b24-4142-a3c7-dfdaf5cf6d96

Adapter
niklasm222

niklasm222

qwen2.5-3b-grpo-1.75k-gsm8k-sp-struct-rwd1-seed

Base
siddhant71197

siddhant71197

less_ful2

Adapter
kiritan

kiritan

iteboshi-tiny

Base
andre-hartiwan

andre-hartiwan

my_awesome_eli5_clm-model

Fine-tuned
charlottemeyer

charlottemeyer

s1.1-20250515_160200

Fine-tuned
Sharpaxis

Sharpaxis

Llama-2-7_Ethical_Guardian

Base
vermoney

vermoney

ab2ddd26-d866-4764-bdc4-da49d809cb5d

Adapter
marialvsantiago

marialvsantiago

46ba82d0-f440-4769-8387-4127feb91180

Adapter
lihengma

lihengma

Llama-3.1-8B-Instruct_2wiki_text_mrl_v1

Base
rayonlabs

rayonlabs

hf-autotrain-2025-05-15-15-1bc612d3

Fine-tuned
mrpeerat

mrpeerat

test-model

Base
Dqdung205

Dqdung205

Vistral

Base
luhaoran

luhaoran

Qwen2.5-7B-Stage2-lora-0447-full-warm0_2

Base
YusufBayram-Personal

YusufBayram-Personal

EleutherAI-pythia-410m_client3_round1

Base
open-unlearning

open-unlearning

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr0.0003_beta30_alpha5_epoch10

Base
open-unlearning

open-unlearning

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr0.0003_beta3_alpha2_epoch5

Base
open-unlearning

open-unlearning

neg_tofu_Llama-3.2-1B-Instruct_retain90_lr1e-05_wd0.01_epoch5

Base
ritishshrirao

ritishshrirao

qwen-vqa-lora

Adapter
open-unlearning

open-unlearning

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkDPO_lr5e-05_beta0.5_alpha1_epoch5

Base
annasoli

annasoli

gemma-3-12b-it_bad-med_full-ft_LR2e-5_3E

Base
open-unlearning

open-unlearning

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr0.0003_beta3_alpha2_epoch10

Base
open-unlearning

open-unlearning

pos_tofu_Llama-3.2-1B-Instruct_retain90_forget10_bio_lr3e-05_wd0.01_epoch5

Base
open-unlearning

open-unlearning

pos_tofu_Llama-3.2-1B-Instruct_full_lr5e-05_wd0.01_epoch5

Base
liuh6

liuh6

whisper-tiny_to_Chinese_accent_PHaPS

Fine-tuned
ASethi04

ASethi04

Qwen-Qwen2.5-7B-pubmedqa-third-full-parameter-1-1e-05-num-epochs-1

Fine-tuned
open-unlearning

open-unlearning

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr0.0003_beta30_alpha5_epoch5

Base
open-unlearning

open-unlearning

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_UNDIAL_lr1e-05_beta30_alpha5_epoch10

Base
open-unlearning

open-unlearning

neg_tofu_Llama-3.2-1B-Instruct_retain90_celeb10_bio_lr5e-05_wd0.01_epoch10

Base
open-unlearning

open-unlearning

neg_tofu_Llama-3.2-1B-Instruct_retain90_celeb10_bio_lr2e-05_wd0.01_epoch10

Base
open-unlearning

open-unlearning

unlearn_tofu_Llama-3.2-1B-Instruct_forget10_NPO_lr1e-05_beta0.5_alpha2_epoch10

Base