TheBloke commited on
Commit
8cea1fd
1 Parent(s): 72b7b83

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -41
README.md CHANGED
@@ -13,17 +13,19 @@ tags:
13
  datasets:
14
  - h2oai/h2ogpt-oig-oasst1-instruct-cleaned-v2
15
  ---
 
16
  <div style="width: 100%;">
17
  <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
18
  </div>
19
  <div style="display: flex; justify-content: space-between; width: 100%;">
20
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
21
- <p><a href="https://discord.gg/UBgz4VXf">Chat & support: my new Discord server</a></p>
22
  </div>
23
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
24
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? Patreon coming soon!</a></p>
25
  </div>
26
  </div>
 
27
 
28
  # h2ogpt-oasst1-512-30B-GGML
29
 
@@ -75,45 +77,30 @@ Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](http
75
 
76
  Note: at this time text-generation-webui may not support the new May 19th llama.cpp quantisation methods for q4_0, q4_1 and q8_0 files.
77
 
78
- def insert_templates_into_file(filename, template1_filename, template2_filename):
79
- with open(filename, 'r') as file:
80
- lines = [line.rstrip() for line in file]
81
-
82
- # Read the contents of the template files
83
- with open(template1_filename, 'r') as file:
84
- template1 = file.read().splitlines()
85
-
86
- with open(template2_filename, 'r') as file:
87
- template2 = file.read().splitlines()
88
-
89
- # Find the line index of the second "---"
90
- indices = [i for i, line in enumerate(lines) if line.strip() == "---"]
91
- if len(indices) < 2:
92
- raise ValueError("File doesn't have two lines with ---")
93
-
94
- second_dash_line_index = indices[1]
95
-
96
- # Insert first template after the second "---"
97
- for i, template_line in enumerate(template1, start=1):
98
- lines.insert(second_dash_line_index + i, template_line)
99
-
100
- original_card_index = 0
101
- # Find the line index of the first occurrence of 'original model card' or '## further info' (case insensitive)
102
- try:
103
- original_card_index = next(i for i, line in enumerate(lines) if 'original model card' in line.lower())
104
- except StopIteration:
105
- try:
106
- original_card_index = next(i for i, line in enumerate(lines) if '## further info' in line.lower())
107
- except StopIteration:
108
- original_card_index = len(lines)
109
-
110
- # Insert second template before the line with 'original model card' or '## further info'
111
- for i, template_line in enumerate(template2, start=1):
112
- lines.insert(original_card_index + i - 1, template_line)
113
-
114
- with open(filename, 'w') as file:
115
- for line in lines:
116
- file.write(line + '\n')
117
 
118
  # Original h2oGPT Model Card
119
  ## Summary
 
13
  datasets:
14
  - h2oai/h2ogpt-oig-oasst1-instruct-cleaned-v2
15
  ---
16
+ <!-- header start -->
17
  <div style="width: 100%;">
18
  <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
19
  </div>
20
  <div style="display: flex; justify-content: space-between; width: 100%;">
21
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
22
+ <p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
23
  </div>
24
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
25
+ <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
26
  </div>
27
  </div>
28
+ <!-- header end -->
29
 
30
  # h2ogpt-oasst1-512-30B-GGML
31
 
 
77
 
78
  Note: at this time text-generation-webui may not support the new May 19th llama.cpp quantisation methods for q4_0, q4_1 and q8_0 files.
79
 
80
+ <!-- footer start -->
81
+ ## Discord
82
+
83
+ For further support, and discussions on these models and AI in general, join us at:
84
+
85
+ [TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
86
+
87
+ ## Thanks, and how to contribute.
88
+
89
+ Thanks to the [chirper.ai](https://chirper.ai) team!
90
+
91
+ 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.
92
+
93
+ 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.
94
+
95
+ Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
96
+
97
+ * Patreon: https://patreon.com/TheBlokeAI
98
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
99
+
100
+ **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.
101
+
102
+ Thank you to all my generous patrons and donaters!
103
+ <!-- footer end -->
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
104
 
105
  # Original h2oGPT Model Card
106
  ## Summary