Instructions to use tutur90/SONAR-Mini-Text-to-Text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tutur90/SONAR-Mini-Text-to-Text with Transformers:

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

pipe = pipeline("text-generation", model="tutur90/SONAR-Mini-Text-to-Text")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("tutur90/SONAR-Mini-Text-to-Text")
model = AutoModelForSeq2SeqLM.from_pretrained("tutur90/SONAR-Mini-Text-to-Text", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tutur90/SONAR-Mini-Text-to-Text with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tutur90/SONAR-Mini-Text-to-Text"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tutur90/SONAR-Mini-Text-to-Text",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tutur90/SONAR-Mini-Text-to-Text

SGLang

How to use tutur90/SONAR-Mini-Text-to-Text 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 "tutur90/SONAR-Mini-Text-to-Text" \
    --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": "tutur90/SONAR-Mini-Text-to-Text",
		"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 "tutur90/SONAR-Mini-Text-to-Text" \
        --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": "tutur90/SONAR-Mini-Text-to-Text",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tutur90/SONAR-Mini-Text-to-Text with Docker Model Runner:
```
docker model run hf.co/tutur90/SONAR-Mini-Text-to-Text
```

SONAR-Mini-Text-to-Text / README.md

tutur90

Upload folder using huggingface_hub

efd9899 verified 11 months ago

preview code

Raw

History Blame Contribute Delete

1.27 kB

metadata

library_name: transformers
base_model: checkpoints/sonar_mini
tags:
  - generated_from_trainer
model-index:
  - name: sonar_mini
    results: []

sonar_mini

This model is a fine-tuned version of checkpoints/sonar_mini on an unknown dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 512
seed: 42
distributed_type: multi-GPU
num_devices: 6
total_train_batch_size: 192
total_eval_batch_size: 3072
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3.0
mixed_precision_training: Native AMP

Framework versions

Transformers 4.53.2
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.21.4