Instructions to use xdatasi/antares-7b-slovenian with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xdatasi/antares-7b-slovenian with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="xdatasi/antares-7b-slovenian")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xdatasi/antares-7b-slovenian")
model = AutoModelForCausalLM.from_pretrained("xdatasi/antares-7b-slovenian")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xdatasi/antares-7b-slovenian with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xdatasi/antares-7b-slovenian"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xdatasi/antares-7b-slovenian",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/xdatasi/antares-7b-slovenian

SGLang

How to use xdatasi/antares-7b-slovenian with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "xdatasi/antares-7b-slovenian" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xdatasi/antares-7b-slovenian",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "xdatasi/antares-7b-slovenian" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xdatasi/antares-7b-slovenian",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use xdatasi/antares-7b-slovenian with Docker Model Runner:
```
docker model run hf.co/xdatasi/antares-7b-slovenian
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

AntaresAI

We introduce Antares-7b-slovenian, an instruction-tuned and alignment model based on Mixtral-8x7B-v0.1 and Llama-2-70b-hf finetuned for Slovenian language.

Please refer to the evaluation results table for details.

Instruction Fine-tuning Strategy

We utilize state-of-the-art instruction fine-tuning methods including supervised fine-tuning (SFT) and direct preference optimization (DPO)

Data Contamination Test Results

Results will be updated soon.

Evaluation Results

Results will be updated soon.

Contact Us

Any questions and suggestions are welcomed at the discussion tab.

Downloads last month: -

Safetensors

Model size

7B params

Tensor type

BF16