Instructions to use zhouxiangxin/Initial-Reasoning-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zhouxiangxin/Initial-Reasoning-4B with Transformers:

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

pipe = pipeline("text-generation", model="zhouxiangxin/Initial-Reasoning-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zhouxiangxin/Initial-Reasoning-4B")
model = AutoModelForCausalLM.from_pretrained("zhouxiangxin/Initial-Reasoning-4B", device_map="auto")
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 zhouxiangxin/Initial-Reasoning-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zhouxiangxin/Initial-Reasoning-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zhouxiangxin/Initial-Reasoning-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zhouxiangxin/Initial-Reasoning-4B

SGLang

How to use zhouxiangxin/Initial-Reasoning-4B 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 "zhouxiangxin/Initial-Reasoning-4B" \
    --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": "zhouxiangxin/Initial-Reasoning-4B",
		"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 "zhouxiangxin/Initial-Reasoning-4B" \
        --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": "zhouxiangxin/Initial-Reasoning-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zhouxiangxin/Initial-Reasoning-4B with Docker Model Runner:
```
docker model run hf.co/zhouxiangxin/Initial-Reasoning-4B
```

Improve model card for Variational Reasoning for Language Models

by nielsr HF Staff - opened Sep 30, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+62

-92

nielsr

Sep 30, 2025

This PR significantly enhances the model card by:

Adding pipeline_tag: text-generation to ensure discoverability for language models.
Adding license: apache-2.0, inferred from the underlying frameworks (LLaMA-Factory and SkyThought) used in the repository.
Including relevant tags: llm, qwen, and reasoning for better categorization and search.
Updating the model card title to "Model Card for Variational Reasoning for Language Models".
Populating the "Model Details" and "Model Sources" sections with comprehensive information from the paper and GitHub repository, including:
- A summary of the model based on the paper's abstract.
- Authors as developers.
- Model type, language, and finetuning details.
- Direct links to the paper: Variational Reasoning for Language Models.
- Direct links to the GitHub repository: https://github.com/sail-sg/variational-reasoning for detailed usage, training, and evaluation instructions.
Adding the BibTeX citation provided in the GitHub README.

Please review and merge these improvements to provide a more informative and discoverable model card.

Improve model card for Variational Reasoning for Language Models1e85aab1

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment