failspy commited on
Commit
0b3b85b
1 Parent(s): 12c4458

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -39,8 +39,8 @@ This model is based on Phi-3-Mini-Instruct-4k, and is governed by the MIT licens
39
 
40
  The base model has 4k context, and the qLoRA fine-tuning was with 4k sequence length.
41
 
42
- The model's weights were then adjusted to ablate and inhibit refusals based on the methodology described in [Refusal in LLMs is mediated by a single direction](https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction)'
43
- This effectively uncensors the model.
44
 
45
  It took 2.5 days on 8xL40S node provided by Crusoe Cloud
46
 
 
39
 
40
  The base model has 4k context, and the qLoRA fine-tuning was with 4k sequence length.
41
 
42
+ The model's weights were then adjusted to ablate and inhibit refusals based on the methodology described in [Refusal in LLMs is mediated by a single direction](https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction)'
43
+ This effectively uncensors the model.
44
 
45
  It took 2.5 days on 8xL40S node provided by Crusoe Cloud
46