Update README.md
Browse files
README.md
CHANGED
@@ -6,15 +6,7 @@ duplicated_from: TheBloke/wizard-vicuna-13B-SuperHOT-8K-fp16
|
|
6 |
|
7 |
<!-- header start -->
|
8 |
<div style="width: 100%;">
|
9 |
-
|
10 |
-
</div>
|
11 |
-
<div style="display: flex; justify-content: space-between; width: 100%;">
|
12 |
-
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
13 |
-
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
|
14 |
-
</div>
|
15 |
-
<div style="display: flex; flex-direction: column; align-items: flex-end;">
|
16 |
-
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
|
17 |
-
</div>
|
18 |
</div>
|
19 |
<!-- header end -->
|
20 |
|
@@ -49,7 +41,7 @@ The provided modelling code, activated with `trust_remote_code=True` will automa
|
|
49 |
from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
|
50 |
import argparse
|
51 |
|
52 |
-
model_name_or_path = "
|
53 |
|
54 |
use_triton = False
|
55 |
|
@@ -97,33 +89,7 @@ Provided in the repo is `llama_rope_scaled_monkey_patch.py`, written by @kaioken
|
|
97 |
|
98 |
It can be theoretically be added to any Python UI or custom code to enable the same result as `trust_remote_code=True`. I have not tested this, and it should be superseded by using `trust_remote_code=True`, but I include it for completeness and for interest.
|
99 |
|
100 |
-
<!-- footer start -->
|
101 |
-
## Discord
|
102 |
-
|
103 |
-
For further support, and discussions on these models and AI in general, join us at:
|
104 |
-
|
105 |
-
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
|
106 |
-
|
107 |
-
## Thanks, and how to contribute.
|
108 |
-
|
109 |
-
Thanks to the [chirper.ai](https://chirper.ai) team!
|
110 |
-
|
111 |
-
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.
|
112 |
-
|
113 |
-
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.
|
114 |
|
115 |
-
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
|
116 |
-
|
117 |
-
* Patreon: https://patreon.com/TheBlokeAI
|
118 |
-
* Ko-Fi: https://ko-fi.com/TheBlokeAI
|
119 |
-
|
120 |
-
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
|
121 |
-
|
122 |
-
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
|
123 |
-
|
124 |
-
Thank you to all my generous patrons and donaters!
|
125 |
-
|
126 |
-
<!-- footer end -->
|
127 |
|
128 |
# Original model card: Kaio Ken's SuperHOT 8K
|
129 |
|
@@ -159,19 +125,6 @@ I trained the LoRA with the following configuration:
|
|
159 |
|
160 |
# Original model card: June Lee's Wizard Vicuna 13B
|
161 |
|
162 |
-
<!-- header start -->
|
163 |
-
<div style="width: 100%;">
|
164 |
-
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
165 |
-
</div>
|
166 |
-
<div style="display: flex; justify-content: space-between; width: 100%;">
|
167 |
-
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
168 |
-
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
|
169 |
-
</div>
|
170 |
-
<div style="display: flex; flex-direction: column; align-items: flex-end;">
|
171 |
-
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
|
172 |
-
</div>
|
173 |
-
</div>
|
174 |
-
<!-- header end -->
|
175 |
# Wizard-Vicuna-13B-HF
|
176 |
|
177 |
This is a float16 HF format repo for [junelee's wizard-vicuna 13B](https://huggingface.co/junelee/wizard-vicuna-13b).
|
@@ -186,30 +139,7 @@ This model was converted to float16 to make it easier to load and manage.
|
|
186 |
* [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/wizard-vicuna-13B-GGML).
|
187 |
* [float16 HF format model for GPU inference](https://huggingface.co/TheBloke/wizard-vicuna-13B-HF).
|
188 |
|
189 |
-
<!-- footer start -->
|
190 |
-
## Discord
|
191 |
-
|
192 |
-
For further support, and discussions on these models and AI in general, join us at:
|
193 |
-
|
194 |
-
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
|
195 |
-
|
196 |
-
## Thanks, and how to contribute.
|
197 |
-
|
198 |
-
Thanks to the [chirper.ai](https://chirper.ai) team!
|
199 |
-
|
200 |
-
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.
|
201 |
-
|
202 |
-
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.
|
203 |
-
|
204 |
-
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
|
205 |
-
|
206 |
-
* Patreon: https://patreon.com/TheBlokeAI
|
207 |
-
* Ko-Fi: https://ko-fi.com/TheBlokeAI
|
208 |
-
|
209 |
-
**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.
|
210 |
|
211 |
-
Thank you to all my generous patrons and donaters!
|
212 |
-
<!-- footer end -->
|
213 |
|
214 |
# Original WizardVicuna-13B model card
|
215 |
|
|
|
6 |
|
7 |
<!-- header start -->
|
8 |
<div style="width: 100%;">
|
9 |
+
Cloned from TheBloke repo
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
</div>
|
11 |
<!-- header end -->
|
12 |
|
|
|
41 |
from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
|
42 |
import argparse
|
43 |
|
44 |
+
model_name_or_path = "gsaivinay/wizard-vicuna-13B-SuperHOT-8K-fp16"
|
45 |
|
46 |
use_triton = False
|
47 |
|
|
|
89 |
|
90 |
It can be theoretically be added to any Python UI or custom code to enable the same result as `trust_remote_code=True`. I have not tested this, and it should be superseded by using `trust_remote_code=True`, but I include it for completeness and for interest.
|
91 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
92 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
93 |
|
94 |
# Original model card: Kaio Ken's SuperHOT 8K
|
95 |
|
|
|
125 |
|
126 |
# Original model card: June Lee's Wizard Vicuna 13B
|
127 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
128 |
# Wizard-Vicuna-13B-HF
|
129 |
|
130 |
This is a float16 HF format repo for [junelee's wizard-vicuna 13B](https://huggingface.co/junelee/wizard-vicuna-13b).
|
|
|
139 |
* [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/wizard-vicuna-13B-GGML).
|
140 |
* [float16 HF format model for GPU inference](https://huggingface.co/TheBloke/wizard-vicuna-13B-HF).
|
141 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
142 |
|
|
|
|
|
143 |
|
144 |
# Original WizardVicuna-13B model card
|
145 |
|