Hugging Face
Models
Datasets
Spaces
Buckets
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
erjigit17
/
embeddinggemma-300m-ane-coreml
Like
1
Feature Extraction
Core ML
apple-neural-engine
embeddings
sentence-similarity
macos
on-device
gemma3
rag
retrieval-augmented-generation
retrieval
vector-search
semantic-search
edge-ai
low-latency
on-device-ai
License:
gemma
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
embeddinggemma-300m-ane-coreml
343 MB
Ctrl+K
Ctrl+K
1 contributor
History:
5 commits
erjigit17
Drop competitor comparisons, add fast-RAG positioning and RAG-related tags
886ec86
verified
about 2 months ago
embeddinggemma-300m-8bit.mlpackage
Fix verify() to check document path too, unify SEQ_LEN/prefixes via config.py, fix GQA doc error
about 2 months ago
.gitattributes
Safe
1.57 kB
Add EmbeddingGemma-300M Core ML / ANE build (8-bit, manual attention rewrite)
about 2 months ago
README.md
Safe
11.2 kB
Drop competitor comparisons, add fast-RAG positioning and RAG-related tags
about 2 months ago
config.py
Safe
420 Bytes
Fix verify() to check document path too, unify SEQ_LEN/prefixes via config.py, fix GQA doc error
about 2 months ago
convert.py
Safe
9.5 kB
Fix verify() to check document path too, unify SEQ_LEN/prefixes via config.py, fix GQA doc error
about 2 months ago
tokenizer.json
Safe
33.4 MB
xet
Add EmbeddingGemma-300M Core ML / ANE build (8-bit, manual attention rewrite)
about 2 months ago
