A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.

70b

328 2 weeks ago

Readme

This is an uncensored version of perplexity-ai/r1-1776-distill-llama-70b created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

For instance:

  How many 'r' characters are there in the word "strawberry"?

References

Huggingface

x.com/support_huihui

Donation

Your donation helps us continue our further development and improvement, a cup of coffee can do it.
  • bitcoin:
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge