SicariusSicariiStuff commited on
Commit
f2fea37
·
verified ·
1 Parent(s): ee8a92f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -2
README.md CHANGED
@@ -37,9 +37,13 @@ Also, **toxic-dpo** and other morbid unalignment datasets were **not** used. I d
37
 
38
  If you ask the assistant to analyze De Sades' work in graphic detail, you will not have refusals from **Negative_LLAMA_70B**.
39
 
 
 
 
40
  ---
41
 
42
  ### TL;DR
 
43
  - Strong **Roleplay & Creative writing** abilities.
44
  - **Less positivity bias**.
45
  - **Very smart** assistant with **low refusals**.
@@ -69,13 +73,15 @@ If you ask the assistant to analyze De Sades' work in graphic detail, you will n
69
 
70
  - Censorship level: <b>Low</b>
71
 
72
- - **waiting eval results / 10** (10 completely uncensored)
73
 
74
 
75
  ## UGI score:
76
 
77
 
78
- Waiting for results.
 
 
79
 
80
  ---
81
 
 
37
 
38
  If you ask the assistant to analyze De Sades' work in graphic detail, you will not have refusals from **Negative_LLAMA_70B**.
39
 
40
+ ## Update on UGI scores: Achieved the highest score in the world as of 13/01/2025 for 70B models
41
+ - See UGI section for more details
42
+
43
  ---
44
 
45
  ### TL;DR
46
+ - **Highest rated 70B model in the world** in the UGI leaderboard
47
  - Strong **Roleplay & Creative writing** abilities.
48
  - **Less positivity bias**.
49
  - **Very smart** assistant with **low refusals**.
 
73
 
74
  - Censorship level: <b>Low</b>
75
 
76
+ - **7 / 10** (10 completely uncensored)
77
 
78
 
79
  ## UGI score:
80
 
81
 
82
+
83
+
84
+ <img src="https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B/resolve/main/Images/UGI_Negative_LLAMA_70B.png" alt="UGI Score" style="width: 100%; min-width: 700px; display: block;">
85
 
86
  ---
87