Instructions to use Sunbird/translate-nllb-1.3b-salt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sunbird/translate-nllb-1.3b-salt with Transformers:

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

pipe = pipeline("text-generation", model="Sunbird/translate-nllb-1.3b-salt")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Sunbird/translate-nllb-1.3b-salt")
model = AutoModelForSeq2SeqLM.from_pretrained("Sunbird/translate-nllb-1.3b-salt")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Sunbird/translate-nllb-1.3b-salt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sunbird/translate-nllb-1.3b-salt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sunbird/translate-nllb-1.3b-salt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Sunbird/translate-nllb-1.3b-salt

SGLang

How to use Sunbird/translate-nllb-1.3b-salt 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 "Sunbird/translate-nllb-1.3b-salt" \
    --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": "Sunbird/translate-nllb-1.3b-salt",
		"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 "Sunbird/translate-nllb-1.3b-salt" \
        --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": "Sunbird/translate-nllb-1.3b-salt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Sunbird/translate-nllb-1.3b-salt with Docker Model Runner:
```
docker model run hf.co/Sunbird/translate-nllb-1.3b-salt
```

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.

Model details

This machine translation model can convert single sentences from and to any combination of the following languages:

ISO 693-3	Language name
eng	English
ach	Acholi
lgg	Lugbara
lug	Luganda
nyn	Runyankole
teo	Ateso

It was trained on the SALT dataset and a variety of additional external data resources, including back-translated news articles, FLORES-200, MT560 and LAFAND-MT. The base model was facebok/nllb-200-1.3B, with tokens adapted to add support for languages not originally included.

Usage example

tokenizer = transformers.NllbTokenizer.from_pretrained(
    'Sunbird/translate-nllb-1.3b-salt')
model = transformers.M2M100ForConditionalGeneration.from_pretrained(
    'Sunbird/translate-nllb-1.3b-salt')

text = 'Where is the hospital?'
source_language = 'eng'
target_language = 'lug'

language_tokens = {
    'eng': 256047,
    'ach': 256111,
    'lgg': 256008,
    'lug': 256110,
    'nyn': 256002,
    'teo': 256006,
}

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
inputs = tokenizer(text, return_tensors="pt").to(device)
inputs['input_ids'][0][0] = language_tokens[source_language]
translated_tokens = model.to(device).generate(
    **inputs,
    forced_bos_token_id=language_tokens[target_language],
    max_length=100,
    num_beams=5,
)

result = tokenizer.batch_decode(
    translated_tokens, skip_special_tokens=True)[0]
# Eddwaliro liri ludda wa?

Evaluation metrics

Results on salt-dev:

Source language	Target language	BLEU
ach	eng	28.371
lgg	eng	30.45
lug	eng	41.978
nyn	eng	32.296
teo	eng	30.422
eng	ach	20.972
eng	lgg	22.362
eng	lug	30.359
eng	nyn	15.305
eng	teo	21.391

Downloads last month: 705

Safetensors

Model size

1B params

Tensor type

F32

Model tree for Sunbird/translate-nllb-1.3b-salt

Base model

facebook/nllb-200-1.3B

Finetuned

(27)

this model

Adapters

3 models

Sunbird
/

translate-nllb-1.3b-salt

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

Model details

Usage example

Evaluation metrics

Model tree for Sunbird/translate-nllb-1.3b-salt

Dataset used to train Sunbird/translate-nllb-1.3b-salt

Spaces using Sunbird/translate-nllb-1.3b-salt 2