Instructions to use Legenddefsx/paralel-tr-en-embedder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Legenddefsx/paralel-tr-en-embedder with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("Legenddefsx/paralel-tr-en-embedder")

sentences = [
    "The weather is lovely today.",
    "It's so sunny outside!",
    "He drove to the stadium."
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

llama-cpp-python

How to use Legenddefsx/paralel-tr-en-embedder with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Legenddefsx/paralel-tr-en-embedder",
	filename="model.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Legenddefsx/paralel-tr-en-embedder with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Legenddefsx/paralel-tr-en-embedder
# Run inference directly in the terminal:
llama cli -hf Legenddefsx/paralel-tr-en-embedder

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Legenddefsx/paralel-tr-en-embedder
# Run inference directly in the terminal:
llama cli -hf Legenddefsx/paralel-tr-en-embedder

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Legenddefsx/paralel-tr-en-embedder
# Run inference directly in the terminal:
./llama-cli -hf Legenddefsx/paralel-tr-en-embedder

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Legenddefsx/paralel-tr-en-embedder
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Legenddefsx/paralel-tr-en-embedder

Use Docker

docker model run hf.co/Legenddefsx/paralel-tr-en-embedder

LM Studio
Jan
Ollama
How to use Legenddefsx/paralel-tr-en-embedder with Ollama:
```
ollama run hf.co/Legenddefsx/paralel-tr-en-embedder
```

Unsloth Studio

How to use Legenddefsx/paralel-tr-en-embedder with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Legenddefsx/paralel-tr-en-embedder to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Legenddefsx/paralel-tr-en-embedder to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Legenddefsx/paralel-tr-en-embedder to start chatting

Atomic Chat new
Docker Model Runner
How to use Legenddefsx/paralel-tr-en-embedder with Docker Model Runner:
```
docker model run hf.co/Legenddefsx/paralel-tr-en-embedder
```

Lemonade

How to use Legenddefsx/paralel-tr-en-embedder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Legenddefsx/paralel-tr-en-embedder

Run and chat with the model

lemonade run user.paralel-tr-en-embedder-{{QUANT_TAG}}

List all available models

lemonade list

Paralel TR-EN Embedder

A bilingual Turkish-English sentence embedding model fine-tuned on 882K parallel translation pairs. Built on BAAI/bge-small-en-v1.5.

Model Overview

Property	Value
Base Model	BAAI/bge-small-en-v1.5
Embedding Dimension	384
Max Sequence Length	64 tokens
Parameters	33M
Training Data	882,555 parallel TR-EN pairs
Loss Function	MultipleNegativesRankingLoss
GGUF Size	64 MB (F16)

Quick Start

Install and load the model:

pip install sentence-transformers

Then in Python:

from sentence_transformers import SentenceTransformer
model = SentenceTransformer("Legenddefsx/paralel-tr-en-embedder")
tr_emb = model.encode("Merhaba, nasilsin?")
en_emb = model.encode("Hello, how are you?")
similarity = model.similarity(tr_emb, en_emb)

GGUF Format

Download and use with llama.cpp:

wget https://huggingface.co/Legenddefsx/paralel-tr-en-embedder/resolve/main/model.gguf
from llama_cpp import Llama
import numpy as np
model = Llama(model_path="./model.gguf", embedding=True)
emb = model.create_embedding("Hello world")["data"][0]["embedding"]

Performance

Evaluated on a held-out set (not seen during training), including correct translations, hard negatives (structurally similar but semantically wrong translations - e.g. wrong tense, wrong pronoun, negation flipped), and unrelated sentence pairs as a control group.

Category	Avg. Cosine Similarity
Correct translations (held-out)	~0.82
Hard negatives (similar structure, wrong meaning)	~0.68
Unrelated sentence pairs	~0.12

Known limitation: the model separates unrelated content well, but fine-grained distinctions (pronoun swaps, tense flips, negation) are not yet fully reliable - some hard-negative pairs score close to or above correct-translation pairs. Treat similarity scores as a relevance signal for coarse retrieval/clustering rather than a precise correctness check. Further hard-negative training is in progress.

Use Cases

Cross-lingual semantic search (coarse retrieval)
Parallel corpus alignment
Bilingual document clustering
Multilingual RAG (as a first-pass retriever, ideally paired with a reranker)

Not recommended as-is for tasks requiring fine-grained correctness judgments (e.g. automatic translation quality scoring).

License

MIT License

Model fine-tuned: 2026-07-29

Downloads last month: -

Safetensors

Model size

33.4M params

Tensor type

F32