TheBloke commited on
Commit
1fed341
1 Parent(s): 2cf45be

Updating model files

Browse files
Files changed (1) hide show
  1. README.md +24 -2
README.md CHANGED
@@ -2,7 +2,7 @@
2
  license: other
3
  library_name: transformers
4
  pipeline_tag: text-generation
5
- datasets:
6
  - RyokoAI/ShareGPT52K
7
  - Hello-SimpleAI/HC3
8
  tags:
@@ -12,6 +12,17 @@ tags:
12
  - gptq
13
  inference: false
14
  ---
 
 
 
 
 
 
 
 
 
 
 
15
  # Koala: A Dialogue Model for Academic Research
16
  This repo contains the weights of the Koala 13B model produced at Berkeley. It is the result of combining the diffs from https://huggingface.co/young-geng/koala with the original Llama 13B model.
17
 
@@ -24,7 +35,7 @@ I have the following Koala model repositories available:
24
  * [Unquantized 13B model in HF format](https://huggingface.co/TheBloke/koala-13B-HF)
25
  * [GPTQ quantized 4bit 13B model in `pt` and `safetensors` formats](https://huggingface.co/TheBloke/koala-13B-GPTQ-4bit-128g)
26
  * [4bit and 5bit models in GGML format for `llama.cpp`](https://huggingface.co/TheBloke/koala-13B-GGML)
27
-
28
  **7B models:**
29
  * [Unquantized 7B model in HF format](https://huggingface.co/TheBloke/koala-7B-HF)
30
  * [Unquantized 7B model in GGML format for llama.cpp](https://huggingface.co/TheBloke/koala-7b-ggml-unquantized)
@@ -85,6 +96,17 @@ PYTHON_PATH="${PWD}:$PYTHONPATH" python \
85
  --tokenizer_path=/content/llama-13b/tokenizer.model
86
  ```
87
 
 
 
 
 
 
 
 
 
 
 
 
88
  ## Further info
89
 
90
  Check out the following links to learn more about the Berkeley Koala model.
 
2
  license: other
3
  library_name: transformers
4
  pipeline_tag: text-generation
5
+ datasets:
6
  - RyokoAI/ShareGPT52K
7
  - Hello-SimpleAI/HC3
8
  tags:
 
12
  - gptq
13
  inference: false
14
  ---
15
+ <div style="width: 100%;">
16
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
+ </div>
18
+ <div style="display: flex; justify-content: space-between; width: 100%;">
19
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
20
+ <p><a href="https://discord.gg/UBgz4VXf">Chat & support: my new Discord server</a></p>
21
+ </div>
22
+ <div style="display: flex; flex-direction: column; align-items: flex-end;">
23
+ <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? Patreon coming soon!</a></p>
24
+ </div>
25
+ </div>
26
  # Koala: A Dialogue Model for Academic Research
27
  This repo contains the weights of the Koala 13B model produced at Berkeley. It is the result of combining the diffs from https://huggingface.co/young-geng/koala with the original Llama 13B model.
28
 
 
35
  * [Unquantized 13B model in HF format](https://huggingface.co/TheBloke/koala-13B-HF)
36
  * [GPTQ quantized 4bit 13B model in `pt` and `safetensors` formats](https://huggingface.co/TheBloke/koala-13B-GPTQ-4bit-128g)
37
  * [4bit and 5bit models in GGML format for `llama.cpp`](https://huggingface.co/TheBloke/koala-13B-GGML)
38
+
39
  **7B models:**
40
  * [Unquantized 7B model in HF format](https://huggingface.co/TheBloke/koala-7B-HF)
41
  * [Unquantized 7B model in GGML format for llama.cpp](https://huggingface.co/TheBloke/koala-7b-ggml-unquantized)
 
96
  --tokenizer_path=/content/llama-13b/tokenizer.model
97
  ```
98
 
99
+ ## Want to support my work?
100
+
101
+ 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.
102
+
103
+ 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.
104
+
105
+ 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.
106
+
107
+ * Patreon: coming soon! (just awaiting approval)
108
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
109
+ * Discord: https://discord.gg/UBgz4VXf
110
  ## Further info
111
 
112
  Check out the following links to learn more about the Berkeley Koala model.