Instructions to use muskch032/Weiver-U1-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use muskch032/Weiver-U1-4B with Transformers:

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

pipe = pipeline("text-generation", model="muskch032/Weiver-U1-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("muskch032/Weiver-U1-4B")
model = AutoModelForCausalLM.from_pretrained("muskch032/Weiver-U1-4B")
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

vLLM

How to use muskch032/Weiver-U1-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "muskch032/Weiver-U1-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "muskch032/Weiver-U1-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/muskch032/Weiver-U1-4B

SGLang

How to use muskch032/Weiver-U1-4B 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 "muskch032/Weiver-U1-4B" \
    --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": "muskch032/Weiver-U1-4B",
		"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 "muskch032/Weiver-U1-4B" \
        --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": "muskch032/Weiver-U1-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use muskch032/Weiver-U1-4B with Docker Model Runner:
```
docker model run hf.co/muskch032/Weiver-U1-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Weiver-U1 (FP32) is the full-precision version of the Weiver-U1 model, provided for research, evaluation, and further fine-tuning. It is based on Qwen3-4B and trained on the same mixed dataset combining DeepSeek-R1–distilled OpenCodeReasoning data and cfahlgren1/react-code-instructions, ensuring strong performance on React and modern web development tasks.

Unlike the quantized and FP16 variants, this release preserves full FP32 precision, making it suitable for detailed analysis, benchmarking, and experimentation with additional training or adaptation techniques.

License

This model is licensed under a custom Research-Only License created by the Weiver-U1 team.

📘 Non-commercial research use only
🚫 No redistribution allowed
📄 See LICENSE for full terms

Downloads last month: -

Safetensors

Model size

4B params

Tensor type

F32

Model tree for muskch032/Weiver-U1-4B

Quantizations

2 models