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