Update README.md
Browse files
README.md
CHANGED
@@ -98,75 +98,6 @@ Thank you to all my generous patrons and donaters.
|
|
98 |
|
99 |
# Original model card: Jon Durin's Airoboros 13B GPT4
|
100 |
|
101 |
-
---
|
102 |
-
inference: false
|
103 |
-
license: other
|
104 |
-
datasets:
|
105 |
-
- jondurbin/airoboros-gpt4
|
106 |
-
---
|
107 |
-
|
108 |
-
<!-- header start -->
|
109 |
-
<div style="width: 100%;">
|
110 |
-
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
111 |
-
</div>
|
112 |
-
<div style="display: flex; justify-content: space-between; width: 100%;">
|
113 |
-
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
114 |
-
<p><a href="https://discord.gg/UBgz4VXf">Chat & support: my new Discord server</a></p>
|
115 |
-
</div>
|
116 |
-
<div style="display: flex; flex-direction: column; align-items: flex-end;">
|
117 |
-
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
|
118 |
-
</div>
|
119 |
-
</div>
|
120 |
-
<!-- header end -->
|
121 |
-
|
122 |
-
# Jon Durin's Airoboros 13B GPT4 fp16
|
123 |
-
|
124 |
-
These files are fp16 pytorch format model files for [Jon Durin's Airoboros 13B GPT4](https://huggingface.co/jondurbin/airoboros-13b-gpt4).
|
125 |
-
|
126 |
-
They are the result of converting the original fp32 model to fp16 for quicker download and easier storage.
|
127 |
-
|
128 |
-
## Repositories available
|
129 |
-
|
130 |
-
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/airoboros-13b-gpt4-GPTQ)
|
131 |
-
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-13b-gpt4-GGML)
|
132 |
-
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/airoboros-13b-gpt4-fp16)
|
133 |
-
|
134 |
-
## Prompt template
|
135 |
-
|
136 |
-
Uses the Vicuna 1.1 format:
|
137 |
-
|
138 |
-
```
|
139 |
-
USER: prompt
|
140 |
-
ASSISTANT:
|
141 |
-
```
|
142 |
-
|
143 |
-
<!-- footer start -->
|
144 |
-
## Discord
|
145 |
-
|
146 |
-
For further support, and discussions on these models and AI in general, join us at:
|
147 |
-
|
148 |
-
[TheBloke AI's Discord server](https://discord.gg/UBgz4VXf)
|
149 |
-
|
150 |
-
## Thanks, and how to contribute.
|
151 |
-
|
152 |
-
Thanks to the [chirper.ai](https://chirper.ai) team!
|
153 |
-
|
154 |
-
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.
|
155 |
-
|
156 |
-
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.
|
157 |
-
|
158 |
-
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits
|
159 |
-
|
160 |
-
* Patreon: https://patreon.com/TheBlokeAI
|
161 |
-
* Ko-Fi: https://ko-fi.com/TheBlokeAI
|
162 |
-
|
163 |
-
**Patreon special mentions**: Aemon Algiz; Dmitiry Samsonov; Jonathan Leane; Illia Dulskyi; Khalefa Al-Ahmad; Nikolai Manek; senxiiz; Talal Aujan; vamX; Eugene Pentland; Lone Striker; Luke Pendergrass; Johann-Peter Hartmann.
|
164 |
-
|
165 |
-
Thank you to all my generous patrons and donaters.
|
166 |
-
<!-- footer end -->
|
167 |
-
|
168 |
-
# Original model card: Jon Durin's Airoboros 13B GPT4
|
169 |
-
|
170 |
## Overview
|
171 |
|
172 |
This is a fine-tuned 13b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
|
|
|
98 |
|
99 |
# Original model card: Jon Durin's Airoboros 13B GPT4
|
100 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
101 |
## Overview
|
102 |
|
103 |
This is a fine-tuned 13b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
|