Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
layoutlm-document-qa
Modelsdocument question answering model by impira · transformers
impira/layoutlm-document-qa -
roberta-base-squad2
Modelsquestion answering model by deepset · transformers
deepset/roberta-base-squad2 -
ggml-vicuna-13b-1.1
Modelsdocument question answering model by eachadea
eachadea/ggml-vicuna-13b-1.1 -
vilt-b32-finetuned-vqa
Modelsvisual question answering model by dandelin · transformers
dandelin/vilt-b32-finetuned-vqa -
MiniCPM-V-2
Modelsvisual question answering model by openbmb · transformers
openbmb/MiniCPM-V-2 -
OmniParser
Modelsimage text to text model by microsoft · transformers
microsoft/OmniParser -
deplot
Modelsvisual question answering model by google · transformers
google/deplot -
mirage
Modelsimage text to text model by Cactus-Compute · cactus-compute
Cactus-Compute/mirage -
Phi-4-multimodal-instruct
Modelsautomatic speech recognition model by microsoft · transformers
microsoft/Phi-4-multimodal-instruct -
blip2-opt-2.7b
Modelsimage text to text model by Salesforce · transformers
Salesforce/blip2-opt-2.7b -
Xiaomi-OCR-0
Modelsimage text to text model by xiaomi-research · transformers
xiaomi-research/Xiaomi-OCR-0 -
VideoJev-4B
Modelsfeature extraction model by ZhuYuhan · transformers
ZhuYuhan/VideoJev-4B -
Xiaomi-OCR-0
Modelsimage text to text model by SeerRay-Lab · transformers
SeerRay-Lab/Xiaomi-OCR-0 -
automatic speech recognition model by nvidia · nemo
nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4 -
Perplexity: Sonar
ModelsSonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...
perplexity/sonar -
Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...
moondream/moondream3-preview -
Moondream: Moondream 3.1
ModelsMoondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...
moondream/moondream3.1-9b-a2b
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.