Open Models, Ready for Production

Featured Models

All Models

37,829 results found

Model NameInputOutputType
llm-lab

llm-lab

AvataraBS

Base

videoscore2

vs2_qwen2_5vl_sft_17k_1e-5_2fps_warm005_8192

Fine-tuned

videoscore2

vs2_qwen2_5vl_sft_17k_3e-5_2fps_8192

Fine-tuned
llm-lab

llm-lab

Avatara-base

Base
madhiai

madhiai

iykons-invoice-extraction-sft-2007-v2

Base
madhiai

madhiai

iykons-invoice-llama-2007

Base

videoscore2

vs2_qwen2_5vl_sft_17k_5e-6_2fps_4096

Fine-tuned
madhiai

madhiai

iykons-invoice-extraction-sft-2007

Base
erdem-erdem

erdem-erdem

ocr2

Base
finalform

finalform

factoryqwen-7B

Adapter
RodrigoR07

RodrigoR07

FinetuneSmolVLMINSTRCUT

Adapter
CraftJarvis

CraftJarvis

base-text-action-qwen2vl-7b-250717-8800-step

Base

videoscore2

vs2_qwen2_5vl_sft_17k_2e-5_2fps_8192

Fine-tuned

videoscore2

vs2_qwen2_5vl_sft_17k_1e-5_2fps_16384

Fine-tuned

HMTBXS

Qwen2.5-VL-3B-Instruct-int4

Base

videoscore2

vs2_qwen2_5vl_sft_17k_1e-5_2fps_8192

Fine-tuned
madhiai

madhiai

invoice-extraction-7B-v4-test

Base
i3ullbum

i3ullbum

VGR-SFT-4ep-jigsaw-2x2

Fine-tuned

aidan-ucc

LoRA-basic-prompt-benthic2600-1epoch-qwen2.5-VL-3B

Fine-tuned

multimodal-reasoning-lab

lora-128

Adapter

hienphantt161

Document-Validation-Qwen2.5-VL

Base

klrq

LoRA_Qwen2.5_VL_7B

Adapter
sungjun12

sungjun12

vlm_confusion_model

Base
i3ullbum

i3ullbum

VGR-SFT-4ep-crop3

Fine-tuned
omlab

omlab

VLM-R1-Qwen2.5VL-3B-OVD-0321

Fine-tuned
ncauchi1

ncauchi1

general_questions_model_v5

Base

avishekjana

llava-v1.6-mistral-7b-FineTuned-custom-docvqa-4bit-0.3-merged

Base

avishekjana

llava-v1.6-mistral-7b-FineTuned-custom-doc-vqa-merged

Base
Adarsh203

Adarsh203

qwen-2.5-vl-7b-invoices_v2

Base

malekwahidi

Prometheus_Qwen2.5_VL_7B_16bit_LoRA

Fine-tuned
joedonino

joedonino

unsloth_qwen25vl7b_product_descriptionv2_fp8

Base

JarvisArt

JarvisArt-Preview

Base
i3ullbum

i3ullbum

VGR-SFT-4ep

Fine-tuned
joedonino

joedonino

unsloth_qwen25vl7b_product_descriptionv2_16bit

Base
NCSOFT

NCSOFT

GME-VARCO-VISION-Embedding

Fine-tuned
tsinghua-ee

tsinghua-ee

video-SALMONN-2_plus_72B

Adapter
tsinghua-ee

tsinghua-ee

video-SALMONN-2_plus_7B

Adapter

YahanYu

sft-box_only

Fine-tuned

YahanYu

sft-box_cot

Fine-tuned

YahanYu

sft-parse_cot

Fine-tuned

YahanYu

sft-parse_only

Fine-tuned
Aurore32

Aurore32

sft_model

Base