Instructions to use tartuNLP/Llammas-translate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tartuNLP/Llammas-translate with Transformers:

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

pipe = pipeline("text-generation", model="tartuNLP/Llammas-translate")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tartuNLP/Llammas-translate")
model = AutoModelForCausalLM.from_pretrained("tartuNLP/Llammas-translate")
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

vLLM

How to use tartuNLP/Llammas-translate with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tartuNLP/Llammas-translate"
# 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/Llammas-translate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tartuNLP/Llammas-translate

SGLang

How to use tartuNLP/Llammas-translate 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/Llammas-translate" \
    --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/Llammas-translate",
		"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/Llammas-translate" \
        --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/Llammas-translate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tartuNLP/Llammas-translate with Docker Model Runner:
```
docker model run hf.co/tartuNLP/Llammas-translate
```

LLammas-translate 🐑

Llama-2-7B finetuned in three stages:

5B tokens of CulturaX (75% Estonain, 25% English)
1M English->Estonian sentence-pairs from CCMatrix (500000), WikiMatrix (400000), Europarl (50000), and OpenSubtitles (50000) as Alpaca-style translation instructions, 25% of the examples are given in opposite direction (Estonian->Englih)
Alpaca-cleaned, Alpaca-est, OASST1 top-1 English conversations, CoT and FLAN-V2 following open-instruct (both 10,000), WMT18 English-Estonian translation development data (as documents), general MTee validation English-Estonian held-out data

Alpaca-est is an instruction dataset generated for Estonian with gpt-3.5-turbo-0613, following Alpaca.

Using the model in a conversational pipeline:

from transformers import pipeline, Conversation
import torch

pipe = pipeline("conversational", model="tartuNLP/Llammas", torch_dtype=torch.bfloat16, device_map="auto")

messages = [
    {"role": "user", "content": "Tere!"},
    {"role": "assistant", "content": "Tere! Kas saaksin teid kuidagi aidata?"},
    {"role": "user", "content": "Kuidas alustada kirja kirjutamist?"}
]

conversation = Conversation(messages)
conversation = pipe(conversation)

Conversational format:

<|user|>
Tere!
<|assistant|>
Tere! Kas saaksin teid kuidagi aidata?</s>
<|user|>
Kuidas alustada kirja kirjutamist?
<|assistant|>
Kirja kirjutamiseks alustage tervitusega, näiteks "Tere!" või "Tere hommikust!". Seejärel tutvustage ennast ja mainige, kellega kirjutate. Kirjeldage oma mõtteid või küsimusi, mida soovite arutada. Lõpetage kiri viisakalt, näiteks "Tänan teid tähelepanu eest!" või "Parimate soovidega!"</s>