Skip to main content

Open Models, Ready for Production

Featured Models

All Models

581,563 results found

Model NameInputOutputType
daixuancheng

daixuancheng

zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step100

Base
tokyotech-llm

tokyotech-llm

Llama-3.1-Swallow-8B-Instruct-v0.5

Fine-tuned
4everStudent

4everStudent

Qwen2-0.5B-GRPO-test-5epochs

Base

windscare2

Lorax

Adapter
daixuancheng

daixuancheng

zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step140

Base
daixuancheng

daixuancheng

ppo_sample8_critic-warm10-lr2e-6_step100_crtic

Base
daixuancheng

daixuancheng

ppo_sac_static0.1_constrainbyadv_step-40_critic

Base
thavens

thavens

pir_sft_ckpt_50_i

Fine-tuned
daixuancheng

daixuancheng

zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix_step40

Base
daixuancheng

daixuancheng

sac-init0.4_qwen-math-7b_constrainbyAdv_yesSuffix_step40

Base
ZhangShenao

ZhangShenao

Llama-3.2-1B

Base
daixuancheng

daixuancheng

ppo_sample8_critic-warm10-lr2e-6_step40_crtic

Base
ZhangShenao

ZhangShenao

Llama-3.2-3B

Base
CezarinniMedia

CezarinniMedia

MacanCa

Adapter
daixuancheng

daixuancheng

ppo_sac_static0.1_constrainbyadv_step-40_actor

Base
alllwang

alllwang

00789f7e-9f45-447f-b541-b4db9c07a00c

Adapter
luckeciano

luckeciano

Qwen-2.5-7B-GRPO-NoBaseline-FisherMaskGlobal-1e-12_7384

Fine-tuned
sinanelms

sinanelms

gemma-3b-hukuk-merged-16bit

Quantized
tamewild

tamewild

4b_v7_merged_e2

Base
tamewild

tamewild

4b_v7_merged_e4

Base

OptShare

resocratic-29k-gpt-4o-PySCIPOpt-sft-Llama-3-8B-Instruct

Base
tamewild

tamewild

4b_v7_merged_e3

Base
Retreatcost

Retreatcost

KansenSakura-Zero-RP-12b

Merged
tamewild

tamewild

4b_v7_merged_e5

Base
gattaplayer

gattaplayer

ugotog-flux-lora32-cosine-1e-4-1536-bs2-v03

Adapter
Aldo789

Aldo789

bd1dea96-c7a0-414c-a16c-cbfe8f765e9c

Base
haihp02

haihp02

Qwen2.5-1.5B-e286e9d0-2a8c-4ad7-9ca3-c5c8dd364d12-DPO_layer_wise_lr

Base
versaceeros

versaceeros

dcf13b53-993f-4b4d-be5b-73a1e0cc78c5

Base

mattfutureflow

matt-images

Adapter
secmlr

secmlr

best_n_no_rationale_poc_agent_withjava_final_model_agent_h100_64step_5epoch

Fine-tuned
mowen222

mowen222

task-10-Qwen-Qwen2.5-7B

Adapter
pankajrajdeo

pankajrajdeo

CT-UMLS-Summarizer-Qwen2.5-3B

Base
AliCat2

AliCat2

Picaro-24b-2506-636

Fine-tuned
SrivatsaBhamidipati

SrivatsaBhamidipati

qwen2.5-coder-3b-qlora

Adapter
BKM1804

BKM1804

Qwen2.5-1.5B-4cc25694-0c92-4c5c-a769-bd8d3bf66b80-SFT_DPO_ratio_2_0

Base
mlfoundations-dev

mlfoundations-dev

openthoughts3_100k_qwen25_1b_bsz1024_lr4e5_epochs5

Fine-tuned
hasdal

hasdal

28686e11-1d59-4507-a11e-28a534a1ed6a

Base
Aldo789

Aldo789

5735a8ff-a67e-4f5a-961e-109d1b911e0f

Base
pankajrajdeo

pankajrajdeo

CT-UMLS-Summarizer-Qwen2.5-3B-4bit

Base
rbelanec

rbelanec

train_qnli_1750781358

Adapter
jenniellama

jenniellama

task-11-Qwen-Qwen2.5-1.5B-Instruct

Adapter
altaweel

altaweel

gemma3-1b-it-ultrasound-merged-v3

Base