Downloads · 30 days
0
Qwen-distill
Smilyai-labs-community/Qwen-distill
Qwen-distill is a text generation model from Smilyai-labs-community. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
A compact, CPU-friendly student distilled from Qwen3-0.6B, optimized for lightweight deployment and real-time chat. Designed for use in browser, Colab, or mobile environments with limited resources.
Access
Public
Updated Jul 29, 2025
Repo size
1.4 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.pt941 MB · 49%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Jul 29, 2025
- Updated
- Jul 29, 2025
- SHA
- f8946c76
Try a prompt
Model card
From the Hugging Face model README
🧠 Qwen3 Distilled Student (0.6B GPT2-style)
A compact, CPU-friendly student distilled from Qwen3-0.6B, optimized for lightweight deployment and real-time chat. Designed for use in browser, Colab, or mobile environments with limited resources.
🏗 Architecture
- Based on
GPT2Configschema for compatibility - Patches applied:
n_inner,layer_norm_epsilon,activation_function, etc.- Handles missing dropout attributes gracefully
- Supports attention streaming and assistant-style prompting
🛠 Training Setup
- Source: Qwen3-0.6B
- Distillation: direct next-token distillation using custom prompt logic
- Platform: Kaggle GPU (A100, 40GB)
- Framework: TensorFlow / PyTorch hybrid flow, minimal dependencies
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Created
- Jul 29, 2025
- Updated
- Jul 29, 2025