Update README.md
Browse files
README.md
CHANGED
@@ -9,7 +9,7 @@ license: other
|
|
9 |
</div>
|
10 |
<div style="display: flex; justify-content: space-between; width: 100%;">
|
11 |
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
12 |
-
<p><a href="https://discord.gg/
|
13 |
</div>
|
14 |
<div style="display: flex; flex-direction: column; align-items: flex-end;">
|
15 |
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
|
@@ -37,7 +37,7 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
|
|
37 |
## Prompt template
|
38 |
|
39 |
```
|
40 |
-
USER: Edit the following for spelling and grammar mistakes:
|
41 |
ASSISTANT:
|
42 |
```
|
43 |
|
@@ -81,7 +81,7 @@ Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](http
|
|
81 |
|
82 |
For further support, and discussions on these models and AI in general, join us at:
|
83 |
|
84 |
-
[TheBloke AI's Discord server](https://discord.gg/
|
85 |
|
86 |
## Thanks, and how to contribute.
|
87 |
|
@@ -91,14 +91,14 @@ I've had a lot of people ask if they can contribute. I enjoy providing models an
|
|
91 |
|
92 |
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.
|
93 |
|
94 |
-
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits
|
95 |
|
96 |
* Patreon: https://patreon.com/TheBlokeAI
|
97 |
* Ko-Fi: https://ko-fi.com/TheBlokeAI
|
98 |
|
99 |
-
**Patreon special mentions**: Aemon Algiz
|
100 |
|
101 |
-
Thank you to all my generous patrons and donaters
|
102 |
<!-- footer end -->
|
103 |
|
104 |
# Original model card: FPHam's Karen The Editor 13B
|
@@ -107,12 +107,12 @@ Thank you to all my generous patrons and donaters.
|
|
107 |
|
108 |
She fixes grammar and wording issues, but doesn't necessary start rewording everything like ChatGPT into a corporate talk. So it should keep the style intact.
|
109 |
|
110 |
-
Based on LLAMA 13b and Wizard-Vucna-uncensored finetune, then finetuned with about 20k grammar examples (bad grammar/good grammar).
|
111 |
|
112 |
Karen gets triggered by this prompt (pun intended):
|
113 |
|
114 |
```
|
115 |
-
USER: Edit the following for spelling and grammar mistakes:
|
116 |
ASSISTANT:
|
117 |
```
|
118 |
|
@@ -129,4 +129,4 @@ context: "Assistant is a meticulous senior editor with a specialization in editi
|
|
129 |
|
130 |
I am not sure to what extend the context part has any effect. Doesn't hurt though.
|
131 |
|
132 |
-
This is a version 0.2 and finetuned just so it retains the underlaying Vicuna qualities.
|
|
|
9 |
</div>
|
10 |
<div style="display: flex; justify-content: space-between; width: 100%;">
|
11 |
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
12 |
+
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
|
13 |
</div>
|
14 |
<div style="display: flex; flex-direction: column; align-items: flex-end;">
|
15 |
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
|
|
|
37 |
## Prompt template
|
38 |
|
39 |
```
|
40 |
+
USER: Edit the following for spelling and grammar mistakes:
|
41 |
ASSISTANT:
|
42 |
```
|
43 |
|
|
|
81 |
|
82 |
For further support, and discussions on these models and AI in general, join us at:
|
83 |
|
84 |
+
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
|
85 |
|
86 |
## Thanks, and how to contribute.
|
87 |
|
|
|
91 |
|
92 |
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.
|
93 |
|
94 |
+
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
|
95 |
|
96 |
* Patreon: https://patreon.com/TheBlokeAI
|
97 |
* Ko-Fi: https://ko-fi.com/TheBlokeAI
|
98 |
|
99 |
+
**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.
|
100 |
|
101 |
+
Thank you to all my generous patrons and donaters!
|
102 |
<!-- footer end -->
|
103 |
|
104 |
# Original model card: FPHam's Karen The Editor 13B
|
|
|
107 |
|
108 |
She fixes grammar and wording issues, but doesn't necessary start rewording everything like ChatGPT into a corporate talk. So it should keep the style intact.
|
109 |
|
110 |
+
Based on LLAMA 13b and Wizard-Vucna-uncensored finetune, then finetuned with about 20k grammar examples (bad grammar/good grammar).
|
111 |
|
112 |
Karen gets triggered by this prompt (pun intended):
|
113 |
|
114 |
```
|
115 |
+
USER: Edit the following for spelling and grammar mistakes:
|
116 |
ASSISTANT:
|
117 |
```
|
118 |
|
|
|
129 |
|
130 |
I am not sure to what extend the context part has any effect. Doesn't hurt though.
|
131 |
|
132 |
+
This is a version 0.2 and finetuned just so it retains the underlaying Vicuna qualities.
|