Instructions to use RUC-DataLab/DeepAnalyze-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RUC-DataLab/DeepAnalyze-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RUC-DataLab/DeepAnalyze-8B")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("RUC-DataLab/DeepAnalyze-8B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use RUC-DataLab/DeepAnalyze-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RUC-DataLab/DeepAnalyze-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RUC-DataLab/DeepAnalyze-8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/RUC-DataLab/DeepAnalyze-8B
- SGLang
How to use RUC-DataLab/DeepAnalyze-8B 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 "RUC-DataLab/DeepAnalyze-8B" \ --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": "RUC-DataLab/DeepAnalyze-8B", "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 "RUC-DataLab/DeepAnalyze-8B" \ --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": "RUC-DataLab/DeepAnalyze-8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use RUC-DataLab/DeepAnalyze-8B with Docker Model Runner:
docker model run hf.co/RUC-DataLab/DeepAnalyze-8B
Improve model card: Update pipeline tag, add library name, and Hugging Face paper link
#2
by nielsr HF Staff - opened
This PR enhances the model card for DeepAnalyze-8B by:
- Updating the
pipeline_tagfromtable-question-answeringtotext-generationto better reflect the model's capabilities as an agentic LLM for autonomous data science, which includes generating reports and analytical insights. - Adding
library_name: transformersmetadata, as the model's architecture (Qwen3ForCausalLM) andtransformers_versioninconfig.jsonindicate compatibility with the Hugging Facetransformerslibrary, enabling the automated code snippet for seamless usage. - Adding a new badge linking to the official Hugging Face paper page (DeepAnalyze: Agentic Large Language Models for Autonomous Data Science) for improved discoverability.
zhangshaolei changed pull request status to merged