README.md

metadata

title: Distilltest
emoji: 💬
colorFrom: yellow
colorTo: purple
sdk: gradio
sdk_version: 5.0.1
app_file: app.py
pinned: false
license: mit
short_description: Uncensored R1 Distill

DeepSeek-R1-Distill-Qwen-1.5B Demo

This is a demonstration of the DeepSeek-R1-Distill-Qwen-1.5B-uncensored model, a lightweight 1.5B parameter language model from ThirdEyeAI. Despite its small size, this model can generate coherent text across various topics.

Features

• Efficient inference with a small memory footprint
• Adjustable generation parameters (length, temperature, top-p)
• Simple interface for text generation

Usage

1. Enter your prompt in the text box
2. Adjust generation parameters if desired
3. Click "Submit" to generate text

Model Information

This space runs the DeepSeek-R1-Distill-Qwen-1.5B-uncensored model from ThirdEyeAI. It's a distilled version of the Qwen architecture, optimized for efficiency while maintaining good performance. The model is available on Hugging Face at thirdeyeai/DeepSeek-R1-Distill-Qwen-1.5B-uncensored.

Limitations

As a small 1.5B parameter model, this LLM has certain limitations:

• Less knowledge than larger models
• More limited reasoning capabilities
• May produce less coherent outputs on complex topics

License

[Include license information for your model]

An example chatbot using Gradio, huggingface_hub, and the Hugging Face Inference API.