Feature Extraction
sentence-transformers
ONNX
Transformers
fastText
sentence-embeddings
sentence-similarity
semantic-search
vector-search
retrieval-augmented-generation
multilingual
cross-lingual
low-resource
merged-model
combined-model
tokenizer-embedded
tokenizer-integrated
standalone
all-in-one
quantized
int8
int8-quantization
optimized
efficient
fast-inference
low-latency
lightweight
small-model
edge-ready
arm64
edge-device
mobile-device
on-device
mobile-inference
tablet
smartphone
embedded-ai
onnx-runtime
onnx-model
MiniLM
MiniLM-L12-v2
paraphrase
usecase-ready
plug-and-play
production-ready
deployment-ready
real-time
distiluse
Update README.md
Browse files
README.md
CHANGED
|
@@ -55,7 +55,7 @@ tags:
|
|
| 55 |
|
| 56 |
---
|
| 57 |
|
| 58 |
-
# 🧠 Unified Multilingual
|
| 59 |
|
| 60 |
This is a highly optimized, quantized, and fully standalone model for **generating sentence embeddings** from **multilingual text**, including Ukrainian, English, Polish, and more.
|
| 61 |
|
|
@@ -74,7 +74,7 @@ Built upon `distiluse-base-multilingual-cased-v2`, the model has been:
|
|
| 74 |
- 🧩 **Single-file architecture**: no need for external tokenizer, vocab, or `transformers` library.
|
| 75 |
- ⚡ **93% faster inference** on mobile compared to the original model.
|
| 76 |
- 🗣️ **Multilingual**: robust across many languages, including low-resource ones.
|
| 77 |
-
- 🧠 **Output = pure embeddings**: pass a string, get a
|
| 78 |
- 🛠️ **Ready for production**: small, fast, accurate, and easy to integrate.
|
| 79 |
- 📱 **Ideal for edge-AI, mobile, and offline scenarios.**
|
| 80 |
|
|
|
|
| 55 |
|
| 56 |
---
|
| 57 |
|
| 58 |
+
# 🧠 Unified Multilingual Distiluse Text Embedder (ONNX + Tokenizer Merged)
|
| 59 |
|
| 60 |
This is a highly optimized, quantized, and fully standalone model for **generating sentence embeddings** from **multilingual text**, including Ukrainian, English, Polish, and more.
|
| 61 |
|
|
|
|
| 74 |
- 🧩 **Single-file architecture**: no need for external tokenizer, vocab, or `transformers` library.
|
| 75 |
- ⚡ **93% faster inference** on mobile compared to the original model.
|
| 76 |
- 🗣️ **Multilingual**: robust across many languages, including low-resource ones.
|
| 77 |
+
- 🧠 **Output = pure embeddings**: pass a string, get a 768-dim vector. That’s it.
|
| 78 |
- 🛠️ **Ready for production**: small, fast, accurate, and easy to integrate.
|
| 79 |
- 📱 **Ideal for edge-AI, mobile, and offline scenarios.**
|
| 80 |
|