Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
FluidInference
/
unlimited-ocr-coreml
Like
0
Follow
Fluid Inference Community
183
Image-Text-to-Text
Core ML
apple
ocr
document-parsing
multi-page
deepseek-ocr
Mixture of Experts
fluidinference
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
unlimited-ocr-coreml
4.09 GB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
alexwengg
Card: decode speed after the attention change
2ab6895
verified
about 17 hours ago
UnlimitedOcrDecoder.mlpackage
Decoder: concatenate attention scores instead of K/V (no per-layer cache copy, ~17% faster decode, same output)
about 17 hours ago
UnlimitedOcrPageEncoder.mlpackage
Unlimited-OCR Core ML: fp16 page encoder + int8 stateful multi-page decoder
about 19 hours ago
.gitattributes
1.57 kB
Unlimited-OCR Core ML: fp16 page encoder + int8 stateful multi-page decoder
about 19 hours ago
LICENSE
Safe
1.06 kB
Unlimited-OCR Core ML: fp16 page encoder + int8 stateful multi-page decoder
about 19 hours ago
README.md
4.18 kB
Card: decode speed after the attention change
about 17 hours ago
config.json
704 Bytes
Unlimited-OCR Core ML: fp16 page encoder + int8 stateful multi-page decoder
about 19 hours ago
embeddings.f16
Safe
331 MB
xet
Unlimited-OCR Core ML: fp16 page encoder + int8 stateful multi-page decoder
about 19 hours ago
tokenizer.json
Safe
9.98 MB
Unlimited-OCR Core ML: fp16 page encoder + int8 stateful multi-page decoder
about 19 hours ago
