Downloads · 30 days
85
4% of all-time downloads
UncensoredLM-DeepSeek-R1-Distill-Qwen-14B
uncensoredai/UncensoredLM-DeepSeek-R1-Distill-Qwen-14B
UncensoredLM-DeepSeek-R1-Distill-Qwen-14B is a machine learning model from uncensoredai. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
An UncensoredLLM with Reasoning, what more could you want? - Note this is an experimental preview and we will continue improving based on feedback, so please good and bad feedback welcome. Leave it in the Community Co…
All-time downloads
1.9K
Public
Parameters
14.2B
3.7 GB on disk
Likes
36
Trending 1
Repo makeup
Click a slice to open those files.
.safetensors28.4 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Jan 30, 2025
- Updated
- Feb 2, 2025
- SHA
- 7786f597
Model card
From the Hugging Face model README
An UncensoredLLM with Reasoning, what more could you want?
-
Note this is an experimental preview and we will continue improving based on feedback, so please good and bad feedback welcome. Leave it in the Community Comments and I will address your feedback asap.
-
Refusal Alignment is pretty clear where we draw the line:
You might be asking yourself: Why Uncensored AI?
Prompt Template the model is trained on:
"instruction,input,output": "The following user query requires an answer that is derived from the context given. It is imperative that the answer is not based on external knowledge or assumptions. Analyze the context thoroughly to extract the necessary information that will form the basis of a clear and accurate answer.<｜User｜>\n%instruction%\n%input%\n<｜Assistant｜>\n%output%",
We just launched our beta, LOOK INTO IT at https://uncensored.ai
- Type
- qwen2
- License
- apache-2.0
- Created
- Jan 30, 2025
- Updated
- Feb 2, 2025