TheBloke commited on
Commit
fff9ac7
1 Parent(s): c20702a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -8
README.md CHANGED
@@ -8,17 +8,19 @@ tags:
8
  - uncensored
9
  inference: true
10
  ---
 
11
  <div style="width: 100%;">
12
  <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
13
  </div>
14
  <div style="display: flex; justify-content: space-between; width: 100%;">
15
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
16
- <p><a href="https://discord.gg/UBgz4VXf">Chat & support: my new Discord server</a></p>
17
  </div>
18
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
19
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? Patreon coming soon!</a></p>
20
  </div>
21
  </div>
 
22
  # Wizard-Vicuna-13B-Uncensored float16 HF
23
 
24
  This is a float16 HF repo for [Eric Hartford's 'uncensored' training of Wizard-Vicuna 13B](https://huggingface.co/ehartford/Wizard-Vicuna-13B-Uncensored).
@@ -31,17 +33,30 @@ It is the result of converting Eric's float32 repo to float16 for easier storage
31
  * [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-GGML).
32
  * [float16 HF format model for GPU inference and further conversions](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-HF).
33
 
34
- ## Want to support my work?
 
35
 
36
- 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.
37
 
38
- So if you're able and willing to contribute, it'd be most gratefully received and will help me to keep providing models, and work on various AI projects.
39
 
40
- 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.
41
 
42
- * Patreon: coming soon! (just awaiting approval)
 
 
 
 
 
 
 
 
43
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
44
- * Discord: https://discord.gg/UBgz4VXf
 
 
 
 
45
  # Original model card
46
 
47
  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.
 
8
  - uncensored
9
  inference: true
10
  ---
11
+ <!-- header start -->
12
  <div style="width: 100%;">
13
  <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
14
  </div>
15
  <div style="display: flex; justify-content: space-between; width: 100%;">
16
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
17
+ <p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
18
  </div>
19
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
20
+ <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
21
  </div>
22
  </div>
23
+ <!-- header end -->
24
  # Wizard-Vicuna-13B-Uncensored float16 HF
25
 
26
  This is a float16 HF repo for [Eric Hartford's 'uncensored' training of Wizard-Vicuna 13B](https://huggingface.co/ehartford/Wizard-Vicuna-13B-Uncensored).
 
33
  * [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-GGML).
34
  * [float16 HF format model for GPU inference and further conversions](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-HF).
35
 
36
+ <!-- footer start -->
37
+ ## Discord
38
 
39
+ For further support, and discussions on these models and AI in general, join us at:
40
 
41
+ [TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
42
 
43
+ ## Thanks, and how to contribute.
44
 
45
+ Thanks to the [chirper.ai](https://chirper.ai) team!
46
+
47
+ I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
48
+
49
+ If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
50
+
51
+ Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
52
+
53
+ * Patreon: https://patreon.com/TheBlokeAI
54
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
55
+
56
+ **Patreon special mentions**: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
57
+
58
+ Thank you to all my generous patrons and donaters!
59
+ <!-- footer end -->
60
  # Original model card
61
 
62
  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.