PierreMesure's picture
Upload model
f737e1c
|
raw
history blame
1.24 kB
---
base_model: KBLab/sentence-bert-swedish-cased
model_creator: KBLab
model_name: sentence-bert-swedish-cased
pipeline_tag: sentence-similarity
lang:
- sv
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
- gguf
license: apache-2.0
language:
- sv
---
# PierreMesure/sentence-bert-swedish-cased-gguf
This is a GGUF conversion of [KBLab/sentence-bert-swedish-cased](https://huggingface.co/KBLab/sentence-bert-swedish-cased) (F32).
I used llama.cpp's script (*convert_hf_to_gguf.py*):
```bash
python convert_hf_to_gguf.py --outtype f32 ./sentence-bert-swedish-cased --outfile ./sentence-bert-swedish-cased.F32.gguf
```
## Usage
You can use this with any tool building on llama.cpp. I made this GGUF to import it in Ollama.
1. Create a *Modelfile*:
```Dockerfile
FROM ./sentence-bert-swedish-cased.F32.gguf
```
Or in one command:
```bash
git clone https://huggingface.co/PierreMesure/sentence-bert-swedish-cased-gguf
cd sentence-bert-swedish-cased-gguf/
echo 'FROM ./sentence-bert-swedish-cased.F32.gguf' > Modelfile
```
2. Import with Ollama
```bash
ollama create sentence-bert-swedish-cased
```