R1 1776 - DeepSeek R1 post-trained to be uncensored and unbiased
R1 1776 is a DeepSeek-R1 reasoning model that has been post-trained by Perplexity AI to remove Chinese Communist Party censorship. The model provides unbiased, accurate, and factual information while maintaining high reasoning capabilities.
Replies
We are truly deep into the era of InfoWars — as one sovereign nation (China) attempts to rewrite history by out-open-sourcing its main rival's LLMs...
FWIW, this gives more credence to the thought that @DeepSeek's launch was indeed a Sputnik moment...!
knowing I can rely on this for factual data without hidden bias makes a big diffrence
Side Space
So, how to use it locally.
@xiaoluoboding download it from Hugging Face and then run it with @LM Studio or @Ollama .