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 is a Qwen3-4B–based model specialized for web development, with a particular focus on React and frontend code generation. It is trained on a mixed dataset combining OpenCodeReasoning (synthetic data distilled from DeepSeek-R1) and cfahlgren1/react-code-instructions, a dataset known to be distilled from Qwen-Coder-32B and DeepSeek-R1. This combination enables the model to retain strong general reasoning abilities while being more effective at generating structured, idiomatic React and web-related code.

The model is fine-tuned using QLoRA and released in both GGUF INT4 (Q4_K_M) and FP16 formats within the same release, allowing users to choose between maximum efficiency or higher numerical precision.

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: -

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

16-bit

Model tree for muskch032/Weiver-U1-4B-GGUF

Base model

muskch032/Weiver-U1-4B

Quantized

(2)

this model