Text Generation
Transformers
Safetensors
English
llama
llama-factory
Not-For-All-Audiences
conversational
text-generation-inference
Inference Endpoints
aaronday3 commited on
Commit
9773b49
1 Parent(s): 645802c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -34,8 +34,9 @@ We trained [LLaMA 3 8B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-
34
  <p style="font-size: 20px; color: red; font-weight: bold;">
35
  IF THE GENERATIONS ARE BAD, REMOVE ALL SYSTEM PROMPTS
36
  </p>
37
- Particularly SillyTavern default prompts can make the model worse. Claude Jailbreaks should work fine though, there was a lot of them in c2 logs.
38
- <br>**You don't need a JB for casual usage but a JB can steer behaviour still.**
 
39
 
40
  ## Sampling
41
 
 
34
  <p style="font-size: 20px; color: red; font-weight: bold;">
35
  IF THE GENERATIONS ARE BAD, REMOVE ALL SYSTEM PROMPTS
36
  </p>
37
+
38
+ **You don't need a JB for casual usage but a JB can steer behaviour still.**
39
+ <br>Particularly SillyTavern default prompts can make the model worse. Claude Jailbreaks should work fine though, there was a lot of them in c2 logs.
40
 
41
  ## Sampling
42