TheBloke commited on
Commit
2209f6d
1 Parent(s): b0ae7d3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -3
README.md CHANGED
@@ -11,7 +11,7 @@ license: other
11
  <p><a href="https://discord.gg/UBgz4VXf">Chat & support: my new Discord server</a></p>
12
  </div>
13
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
14
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? Patreon coming soon!</a></p>
15
  </div>
16
  </div>
17
 
@@ -65,7 +65,9 @@ If you want to have a chat-style conversation, replace the `-p <PROMPT>` argumen
65
 
66
  Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
67
 
68
- ## Want to support my work?
 
 
69
 
70
  I've had a lot of people ask if they can contribute. I love providing models and helping people, but it is starting to rack up pretty big cloud computing bills.
71
 
@@ -73,8 +75,24 @@ So if you're able and willing to contribute, it'd be most gratefully received an
73
 
74
  Donaters will get priority support on any and all AI/LLM/model questions, and I'll gladly quantise any model you'd like to try.
75
 
76
- * Patreon: coming soon! (just awaiting approval)
77
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
78
  * Discord: https://discord.gg/UBgz4VXf
79
 
 
 
80
  # Original model card: Eric Hartford's Wizard Vicuna 30B Uncensored
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  <p><a href="https://discord.gg/UBgz4VXf">Chat & support: my new Discord server</a></p>
12
  </div>
13
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
14
+ <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon</a></p>
15
  </div>
16
  </div>
17
 
 
65
 
66
  Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
67
 
68
+ ## Thanks, and how to support.
69
+
70
+ Thanks to the [chirper.ai](https://chirper.ai) team!
71
 
72
  I've had a lot of people ask if they can contribute. I love providing models and helping people, but it is starting to rack up pretty big cloud computing bills.
73
 
 
75
 
76
  Donaters will get priority support on any and all AI/LLM/model questions, and I'll gladly quantise any model you'd like to try.
77
 
78
+ * Patreon: https://patreon.com/TheBlokeAI
79
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
80
  * Discord: https://discord.gg/UBgz4VXf
81
 
82
+ Patreon special mention: Jonathan Leane; Talal Aujan. Thank you both, and to all my other patrons and donaters.
83
+
84
  # Original model card: Eric Hartford's Wizard Vicuna 30B Uncensored
85
+
86
+ This is [wizard-vicuna-13b](https://huggingface.co/junelee/wizard-vicuna-13b) trained with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.
87
+
88
+ Shout out to the open source AI/ML community, and everyone who helped me out.
89
+
90
+ Note:
91
+
92
+ An uncensored model has no guardrails.
93
+
94
+ You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car.
95
+
96
+ Publishing anything this model generates is the same as publishing it yourself.
97
+
98
+ You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.