Instructions to use zhouxiangxin/Initial-Reasoning-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zhouxiangxin/Initial-Reasoning-8B with Transformers:

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

pipe = pipeline("text-generation", model="zhouxiangxin/Initial-Reasoning-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zhouxiangxin/Initial-Reasoning-8B")
model = AutoModelForCausalLM.from_pretrained("zhouxiangxin/Initial-Reasoning-8B", 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-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zhouxiangxin/Initial-Reasoning-8B"
# 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-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zhouxiangxin/Initial-Reasoning-8B

SGLang

How to use zhouxiangxin/Initial-Reasoning-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 "zhouxiangxin/Initial-Reasoning-8B" \
    --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-8B",
		"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-8B" \
        --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-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zhouxiangxin/Initial-Reasoning-8B with Docker Model Runner:
```
docker model run hf.co/zhouxiangxin/Initial-Reasoning-8B
```

Improve model card for Variational Reasoning for Language Models with metadata, links, and citation

by nielsr HF Staff - opened Sep 30, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+32

-65

nielsr

Sep 30, 2025

This PR significantly enhances the model card by adding essential metadata and detailed information derived from the paper and its official GitHub repository.

Key changes include:

Adding pipeline_tag: text-generation to the YAML metadata for improved discoverability on the Hugging Face Hub.
Updating the model description with details from the paper abstract.
Providing explicit links to the paper (Variational Reasoning for Language Models) and the code repository (https://github.com/sail-sg/variational-reasoning).
Populating fields like Developed by, Model type, Language(s), and Finetuned from model based on available information.
Adding the BibTeX citation as provided in the GitHub README.
Directing users to the GitHub repository for detailed usage instructions, as no explicit sample code was found in the provided context.

These updates aim to provide users with a more comprehensive understanding of the model and its origins.

Improve model card for Variational Reasoning for Language Models with metadata, links, and citationd60cf553

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