|
|
--- |
|
|
title: Uncensored Deepseek Qwen 14B |
|
|
emoji: 🧠 |
|
|
colorFrom: indigo |
|
|
colorTo: blue |
|
|
sdk: gradio |
|
|
python_version: 3.11 |
|
|
app_file: app.py |
|
|
--- |
|
|
|
|
|
sdk_version: 4.43.0 |
|
|
suggested_hardware: a100-large |
|
|
suggested_storage: large |
|
|
app_file: app.py |
|
|
app_port: 7860 |
|
|
fullWidth: true |
|
|
header: mini |
|
|
short_description: Large Uncensored Model powered by Qwen-14B Distill |
|
|
tags: |
|
|
- text-generation |
|
|
- qwen |
|
|
- uncensored |
|
|
- deepseek |
|
|
models: |
|
|
- uncensoredai/UncensoredLM-DeepSeek-R1-Distill-Qwen-14B |
|
|
preload_from_hub: |
|
|
- uncensoredai/UncensoredLM-DeepSeek-R1-Distill-Qwen-14B |
|
|
--- |
|
|
# 🧠 Uncensored DeepSeek Qwen 14B |
|
|
|
|
|
This Space runs the **UncensoredLM-DeepSeek-R1-Distill-Qwen-14B** model using the Text Generation Web UI. |
|
|
It supports long-context chat, system prompts, and instruction tuning. |
|
|
|
|
|
### 🔧 Features |
|
|
- Full 14B parameter model (Distilled from Qwen) |
|
|
- Mixed precision for performance |
|
|
- Context length up to 131K tokens |
|
|
- Thai + English bilingual support |
|
|
- Gradio 4.43 interface |
|
|
|
|
|
### 💡 Usage |
|
|
1. Type your message in the chat box. |
|
|
2. Click “Generate”. |
|
|
3. Enjoy smooth, uncensored text generation. |
|
|
|
|
|
--- |
|
|
|
|
|
🛠️ Built with ❤️ by **โน๊ต** |
|
|
Running on Hugging Face Spaces (Gradio SDK) |
