Instructions to use aurora-m/aurora-m-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aurora-m/aurora-m-instruct with Transformers:

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

pipe = pipeline("text-generation", model="aurora-m/aurora-m-instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aurora-m/aurora-m-instruct")
model = AutoModelForCausalLM.from_pretrained("aurora-m/aurora-m-instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aurora-m/aurora-m-instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/aurora-m/aurora-m-instruct

SGLang

How to use aurora-m/aurora-m-instruct 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 "aurora-m/aurora-m-instruct" \
    --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": "aurora-m/aurora-m-instruct",
		"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 "aurora-m/aurora-m-instruct" \
        --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": "aurora-m/aurora-m-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aurora-m/aurora-m-instruct with Docker Model Runner:
```
docker model run hf.co/aurora-m/aurora-m-instruct
```

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.

Aurora-m1-instruct

Open Source Continual Pre-training for Multilingual Language and Code

Model Description

This is a experimental research Instruct Version of Aurora-m, a Starcoderplus

Usage

Aurora-m is a continued pretrain model with a very small instruction set mixed in. It was then instruct tuned further, but you will get better performance by further tuning the model. Also, while the model will respond to multilingual instructions, the model was trained on predominantly English instructions, so multilingual instruction finetuning is recommended.

The instruction format we used is:

### Instruction:
{instruction}
### Response:

Downloads last month: 2

Safetensors

Model size

15B params

Tensor type

F32

Model tree for aurora-m/aurora-m-instruct

Base model

bigcode/starcoderplus

Finetuned

(2)

this model

aurora-m
/

aurora-m-instruct