Instructions to use zjunlp/DataMind-Analysis-Qwen2.5-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zjunlp/DataMind-Analysis-Qwen2.5-14B with Transformers:

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

pipe = pipeline("text-generation", model="zjunlp/DataMind-Analysis-Qwen2.5-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zjunlp/DataMind-Analysis-Qwen2.5-14B")
model = AutoModelForCausalLM.from_pretrained("zjunlp/DataMind-Analysis-Qwen2.5-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zjunlp/DataMind-Analysis-Qwen2.5-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zjunlp/DataMind-Analysis-Qwen2.5-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zjunlp/DataMind-Analysis-Qwen2.5-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zjunlp/DataMind-Analysis-Qwen2.5-14B

SGLang

How to use zjunlp/DataMind-Analysis-Qwen2.5-14B 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 "zjunlp/DataMind-Analysis-Qwen2.5-14B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zjunlp/DataMind-Analysis-Qwen2.5-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "zjunlp/DataMind-Analysis-Qwen2.5-14B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zjunlp/DataMind-Analysis-Qwen2.5-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zjunlp/DataMind-Analysis-Qwen2.5-14B with Docker Model Runner:
```
docker model run hf.co/zjunlp/DataMind-Analysis-Qwen2.5-14B
```

Improve model card: Add metadata tags, correct license, and expand content

by nielsr HF Staff - opened Aug 6, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+87

-11

nielsr

Aug 6, 2025

This PR significantly improves the model card for DataMind-Qwen2.5-14B by:

Correcting the license to apache-2.0 as explicitly stated in the associated GitHub repository.
Adding pipeline_tag: text-generation to ensure proper categorization and enable the "Use in Transformers" widget on the Hugging Face Hub.
Adding library_name: transformers to indicate compatibility with the Hugging Face Transformers library.
Integrating the paper's abstract, a direct link to the paper on Hugging Face Papers, and the project's GitHub repository link for easy access to critical information.
Incorporating additional sections from the official GitHub README, including "News", "Training" details, and "Contributors", to provide a more comprehensive and useful overview of the DataMind project.
Updating the "Evaluation" section to include the data download script, aligning with the latest information from the GitHub repository.

These updates aim to provide a more informative and user-friendly model card for researchers and developers.

Improve model card: Add metadata tags, correct license, and expand contente5b5b18b

Yukirsh changed pull request status to merged Aug 12, 2025

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