Instructions to use UniverseTBD/astrollama-7b-chat-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UniverseTBD/astrollama-7b-chat-alpha with Transformers:

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

pipe = pipeline("text-generation", model="UniverseTBD/astrollama-7b-chat-alpha")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("UniverseTBD/astrollama-7b-chat-alpha")
model = AutoModelForCausalLM.from_pretrained("UniverseTBD/astrollama-7b-chat-alpha")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use UniverseTBD/astrollama-7b-chat-alpha with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UniverseTBD/astrollama-7b-chat-alpha"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UniverseTBD/astrollama-7b-chat-alpha",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/UniverseTBD/astrollama-7b-chat-alpha

SGLang

How to use UniverseTBD/astrollama-7b-chat-alpha 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 "UniverseTBD/astrollama-7b-chat-alpha" \
    --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": "UniverseTBD/astrollama-7b-chat-alpha",
		"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 "UniverseTBD/astrollama-7b-chat-alpha" \
        --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": "UniverseTBD/astrollama-7b-chat-alpha",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use UniverseTBD/astrollama-7b-chat-alpha with Docker Model Runner:
```
docker model run hf.co/UniverseTBD/astrollama-7b-chat-alpha
```

AstroLLaMA Chat

Check out the model in our Hugging Face space!

universeTBD/astrollama-7b-chat-alpha

Model description

This model is a fine-tuned version of universeTBD/astrollama-7b-alpha on a mix of various open-source conversational datasets, as specified in our research note.

The underlying model of AstroLLaMA 7B Alpha is Llama 2 7B, which has been trained using 300k arXiv astro-ph abstracts, introductions, and conclusions. For more information, please refer to the research note.

Intended uses & limitations

With the release of this alpha model, we hope to inspire more astronomers to explore the fine tuning of smaller models.

Please be advised, that the alpha version of our model may not be perfect and robust. At times, it might generate strange or confusing outputs. As this is an alpha version, it has not been aligned with safety guidelines, making it potentially susceptible to misuse.

Model usage

To achieve the desired features and performance from the chat model, it is essential to adhere to a specific formatting, which is the following: ###Human: {content}, ###Assistant: {content}.

Downloads last month: 13

Safetensors

Model size

7B params

Tensor type

F16

Model tree for UniverseTBD/astrollama-7b-chat-alpha

Base model

UniverseTBD/astrollama-7b-alpha

Finetuned

(1)

this model