Instructions to use AstronMarket/Raven-Reasoning-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AstronMarket/Raven-Reasoning-Model with Transformers:

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

pipe = pipeline("text-generation", model="AstronMarket/Raven-Reasoning-Model")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AstronMarket/Raven-Reasoning-Model", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AstronMarket/Raven-Reasoning-Model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AstronMarket/Raven-Reasoning-Model

SGLang

How to use AstronMarket/Raven-Reasoning-Model 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 "AstronMarket/Raven-Reasoning-Model" \
    --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": "AstronMarket/Raven-Reasoning-Model",
		"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 "AstronMarket/Raven-Reasoning-Model" \
        --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": "AstronMarket/Raven-Reasoning-Model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AstronMarket/Raven-Reasoning-Model with Docker Model Runner:
```
docker model run hf.co/AstronMarket/Raven-Reasoning-Model
```

Request: DOI

by Paradigm5h1f7 - opened Jan 22

Discussion

Paradigm5h1f7

Jan 22

The name of the model caught my attention. Curious what is needed to be allowed access to download?
Regards,
Aizen

saumilyajj

Raven org Mar 14

Hi Aizen,

Thank you for your interest in the Raven Reasoning Model. At the moment, the model is closed because we are still in the early stages of building our Web3 startup. However, we do plan to make the model open source in the future so that others can explore and use it.

For the latest updates, you can follow Astron Markets on X: https://x.com/Astron_Markets

You can also connect with me directly on X: https://x.com/Saumilya_gupta

Best regards,
Saumilya Gupta

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment