Instructions to use tartuNLP/Llama-SMUGRI-7B-Instruct-MTI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tartuNLP/Llama-SMUGRI-7B-Instruct-MTI with Transformers:

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

pipe = pipeline("text-generation", model="tartuNLP/Llama-SMUGRI-7B-Instruct-MTI", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tartuNLP/Llama-SMUGRI-7B-Instruct-MTI")
model = AutoModelForCausalLM.from_pretrained("tartuNLP/Llama-SMUGRI-7B-Instruct-MTI", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tartuNLP/Llama-SMUGRI-7B-Instruct-MTI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tartuNLP/Llama-SMUGRI-7B-Instruct-MTI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tartuNLP/Llama-SMUGRI-7B-Instruct-MTI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tartuNLP/Llama-SMUGRI-7B-Instruct-MTI

SGLang

How to use tartuNLP/Llama-SMUGRI-7B-Instruct-MTI 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 "tartuNLP/Llama-SMUGRI-7B-Instruct-MTI" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tartuNLP/Llama-SMUGRI-7B-Instruct-MTI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "tartuNLP/Llama-SMUGRI-7B-Instruct-MTI" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tartuNLP/Llama-SMUGRI-7B-Instruct-MTI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tartuNLP/Llama-SMUGRI-7B-Instruct-MTI with Docker Model Runner:
```
docker model run hf.co/tartuNLP/Llama-SMUGRI-7B-Instruct-MTI
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-SMUGRI-7B-Instruct-MTI

An instruction-tuned version of tartuNLP/Llama-SMUGRI-7B base model continually pre-trained from meta-llama/Llama-2-7b-hf to support Võro, Komi, and Livonian. The model additionally supports English, Estonian, Finnish, and Russian, however those languages were not the focus.

The instruction-tuning dataset consists of supporting instructions in Estonian, Finnish, English, and Russian, and Alpaca-style instructions translated into Võro, Livonian, and Komi with Neurotõlge. See our paper for more details (model referenced as Llama-SMUGRI-Instruct SupInst+TrAlpaca).

Usage

We trained and evaluated our model with transformers==4.36.2.

Example usage:

from transformers import pipeline
import torch

pipe = pipeline("text-generation", model="tartuNLP/Llama-SMUGRI-7B-Instruct-MTI", torch_dtype=torch.bfloat16, device_map="auto")

messages = [
    {"role": "user", "content": "Kolm nõvvo, et terveq püssüq."},
]

prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.6, top_k=50, top_p=0.9)
print(outputs[0]["generated_text"][len(prompt):])

Citation

@misc{purason2024llmsextremelylowresourcefinnougric,
      title={LLMs for Extremely Low-Resource Finno-Ugric Languages}, 
      author={Taido Purason and Hele-Andra Kuulmets and Mark Fishel},
      year={2024},
      eprint={2410.18902},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2410.18902}, 
}