Instructions to use KBLab/sentence-bert-swedish-cased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KBLab/sentence-bert-swedish-cased with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("KBLab/sentence-bert-swedish-cased")

sentences = [
    "Mannen åt mat.",
    "Han förtärde en närande och nyttig måltid.",
    "Det var ett sunkigt hak med ganska gott käk.",
    "Han inmundigade middagen tillsammans med ett glas rödvin.",
    "Potatischips är jättegoda.",
    "Tryck på knappen för att få tala med kundsupporten."
]
embeddings = model.encode(sentences)

similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [6, 6]

Transformers

How to use KBLab/sentence-bert-swedish-cased with Transformers:

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("KBLab/sentence-bert-swedish-cased")
model = AutoModel.from_pretrained("KBLab/sentence-bert-swedish-cased", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use KBLab/sentence-bert-swedish-cased with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible embeddings server:
llama serve -hf KBLab/sentence-bert-swedish-cased:BF16 --embeddings

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible embeddings server:
llama serve -hf KBLab/sentence-bert-swedish-cased:BF16 --embeddings

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible embeddings server:
./llama-server -hf KBLab/sentence-bert-swedish-cased:BF16 --embeddings

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 embeddings server:
./build/bin/llama-server -hf KBLab/sentence-bert-swedish-cased:BF16 --embeddings

Llama new
LM Studio
Jan
Ollama
How to use KBLab/sentence-bert-swedish-cased with Ollama:
```
ollama run hf.co/KBLab/sentence-bert-swedish-cased:BF16
```
Unsloth Desktop
Docker Model Runner
How to use KBLab/sentence-bert-swedish-cased with Docker Model Runner:
```
docker model run hf.co/KBLab/sentence-bert-swedish-cased:BF16
```

Lemonade

How to use KBLab/sentence-bert-swedish-cased with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KBLab/sentence-bert-swedish-cased:BF16

Run and chat with the model

lemonade run user.sentence-bert-swedish-cased-BF16

List all available models

lemonade list

Atomic Chat

sentence-bert-swedish-cased / sentence_bert_config.json

Lauler

original model trained with longer paragraphs, max seq len 384

ace3987 almost 4 years ago

Raw History Blame

53 Bytes

{
  "max_seq_length": 384,
  "do_lower_case": false
}