Skip to main content

Open Models, Ready for Production

Featured Models

All Models

582,019 results found

Model NameInputOutputType
hsicat

hsicat

m3_pyDPO

Base
Muennighoff

Muennighoff

Qwen2.5-1.5B-hl-true-v5

Fine-tuned
YunTaekhan

YunTaekhan

gemma-3-finetune-4B-esports

Fine-tuned
AdamGalczynski

AdamGalczynski

gemma-2b-sql-finetuned

Base
coralieb7

coralieb7

julien-mcqa-sft-TULUv3unshuffled200k-dpo-sciqarc3000

Base
BootesVoid

BootesVoid

cmbf6yim100h6nfhi2tj599e1_cmbhwag8j087ckfxs0bs8j2j1

Adapter
sugilee

sugilee

mental-health-distill

Base
davgauch

davgauch

MNLP_M3_mcqa_mixed_rationale_v6

Fine-tuned
omkargarud

omkargarud

Genius

Base
yinita

yinita

cpdc-qwen14-base-task1-v0-lora-cp

Adapter
johnnyd-gensyn

johnnyd-gensyn

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_strong_hare

Fine-tuned
syvai

syvai

no-emotion-reasoning-1b

Fine-tuned
syvai

syvai

emotion-reasoning-1b

Fine-tuned
AngelRaychev

AngelRaychev

1.5B-value-iteration_2

Base
smirki

smirki

uigen-t3-preview

Fine-tuned
apriasmoro

apriasmoro

782bceb3-3555-462c-b396-6c6ba8851fc2

Adapter
NurErtug

NurErtug

MNLP_M3_mcqa_model_merged_arc

Base
BootesVoid

BootesVoid

cmbd93ufs038510ozytwnba6h_cmbhwll9z088vkfxs0le7zfcc

Adapter
luyotw

luyotw

openfun-ivod-whisper-medium-negotiation-10-125

Fine-tuned

nengjanggo

test

Base
BensonW

BensonW

EAI-Final-LoRA-1B

Adapter
koreankiwi99

koreankiwi99

dpo_model_mnlp_aggregate_134916

Base
onxtorlo

onxtorlo

pja-model_ver2.2

Base
yolay

yolay

RAIF-DeepScaleR-1.5B

Fine-tuned
HAissa

HAissa

last_sft_15000_with_grpo_3500

Base
vidyc

vidyc

tulu_dpo_small_beta_lr7e5_2epoch

Base
moazeldegwy

moazeldegwy

Qwen3-1.7B-CoachAgent

Fine-tuned
yolay

yolay

RAIF-Qwen2.5-1.5B

Fine-tuned
yolay

yolay

RAIF-DeepSeek-Qwen-7B

Fine-tuned
ema1234

ema1234

qwen_mcqa_bnb_fp4

Base
ema1234

ema1234

qwen_mcqa_bnb_nf4

Base
c0ntrolZ

c0ntrolZ

quality-base

Base
AIgotahole

AIgotahole

L3-DN-8B-v0

Merged
ema1234

ema1234

qwen_mcqa_bnb_llm_int8

Base
Veiterr

Veiterr

MNLP_M2_dpo_model_unsloth_sft

Base
Fulstac

Fulstac

deepseek-r1-Distill-Qwen-32B-lora-4bit-v1

Fine-tuned
Swekerr

Swekerr

LlamaLaTeXeR

Base
Muennighoff

Muennighoff

Qwen2.5-1.5B-hl-false

Fine-tuned
BootesVoid

BootesVoid

cmbhu3829082qkfxsbdwjenvo_cmbhuor5l084ckfxs267gx2y9

Adapter
BootesVoid

BootesVoid

cmbhu888r083bkfxsdxzfd5m3_cmbhujmty083zkfxsll6dpz1u

Adapter
Rudra360

Rudra360

model

Fine-tuned
sergbese

sergbese

gemma-3-isv-translator-v5-merged

Fine-tuned