TheBloke commited on
Commit
8ac7015
1 Parent(s): 8ae2cf8

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +40 -19
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  inference: false
3
- license: other
4
  model_creator: Caleb Morgan
5
  model_link: https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
6
  model_name: Chronos Beluga v2 13B
@@ -9,17 +9,20 @@ quantized_by: TheBloke
9
  ---
10
 
11
  <!-- header start -->
12
- <div style="width: 100%;">
13
- <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 
14
  </div>
15
  <div style="display: flex; justify-content: space-between; width: 100%;">
16
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
17
- <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
18
  </div>
19
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
20
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
21
  </div>
22
  </div>
 
 
23
  <!-- header end -->
24
 
25
  # Chronos Beluga v2 13B - GGML
@@ -30,6 +33,13 @@ quantized_by: TheBloke
30
 
31
  This repo contains GGML format model files for [Caleb Morgan's Chronos Beluga v2 13B](https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16).
32
 
 
 
 
 
 
 
 
33
  GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
34
  * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Supports NVidia CUDA GPU acceleration.
35
  * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a powerful GGML web UI with GPU acceleration on all platforms (CUDA and OpenCL). Especially good for story telling.
@@ -41,7 +51,8 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
41
  ## Repositories available
42
 
43
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GPTQ)
44
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML)
 
45
  * [Caleb Morgan's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16)
46
 
47
  ## Prompt template: Alpaca
@@ -53,14 +64,19 @@ Below is an instruction that describes a task. Write a response that appropriate
53
  {prompt}
54
 
55
  ### Response:
 
56
  ```
57
 
58
  <!-- compatibility_ggml start -->
59
  ## Compatibility
60
 
61
- These quantised GGML files are compatible with llama.cpp as of June 6th, commit `2d43387`.
 
 
62
 
63
- They should also be compatible with all UIs, libraries and utilities which use GGML.
 
 
64
 
65
  ## Explanation of the new k-quant methods
66
  <details>
@@ -83,17 +99,17 @@ Refer to the Provided Files table below to see what files use which methods, and
83
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
84
  | ---- | ---- | ---- | ---- | ---- | ----- |
85
  | [chronos-beluga-v2-13b.ggmlv3.q2_K.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q2_K.bin) | q2_K | 2 | 5.51 GB| 8.01 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
86
- | [chronos-beluga-v2-13b.ggmlv3.q3_K_L.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q3_K_L.bin) | q3_K_L | 3 | 6.93 GB| 9.43 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
87
- | [chronos-beluga-v2-13b.ggmlv3.q3_K_M.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q3_K_M.bin) | q3_K_M | 3 | 6.31 GB| 8.81 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
88
  | [chronos-beluga-v2-13b.ggmlv3.q3_K_S.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q3_K_S.bin) | q3_K_S | 3 | 5.66 GB| 8.16 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
 
 
89
  | [chronos-beluga-v2-13b.ggmlv3.q4_0.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q4_0.bin) | q4_0 | 4 | 7.37 GB| 9.87 GB | Original quant method, 4-bit. |
90
- | [chronos-beluga-v2-13b.ggmlv3.q4_1.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q4_1.bin) | q4_1 | 4 | 8.17 GB| 10.67 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
91
- | [chronos-beluga-v2-13b.ggmlv3.q4_K_M.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q4_K_M.bin) | q4_K_M | 4 | 7.87 GB| 10.37 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
92
  | [chronos-beluga-v2-13b.ggmlv3.q4_K_S.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q4_K_S.bin) | q4_K_S | 4 | 7.37 GB| 9.87 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
 
 
93
  | [chronos-beluga-v2-13b.ggmlv3.q5_0.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q5_0.bin) | q5_0 | 5 | 8.97 GB| 11.47 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
94
- | [chronos-beluga-v2-13b.ggmlv3.q5_1.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q5_1.bin) | q5_1 | 5 | 9.78 GB| 12.28 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
95
- | [chronos-beluga-v2-13b.ggmlv3.q5_K_M.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q5_K_M.bin) | q5_K_M | 5 | 9.23 GB| 11.73 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
96
  | [chronos-beluga-v2-13b.ggmlv3.q5_K_S.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q5_K_S.bin) | q5_K_S | 5 | 8.97 GB| 11.47 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
 
 
97
  | [chronos-beluga-v2-13b.ggmlv3.q6_K.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q6_K.bin) | q6_K | 6 | 10.68 GB| 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K for all tensors - 6-bit quantization |
98
  | [chronos-beluga-v2-13b.ggmlv3.q8_0.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q8_0.bin) | q8_0 | 8 | 13.79 GB| 16.29 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
99
 
@@ -101,10 +117,12 @@ Refer to the Provided Files table below to see what files use which methods, and
101
 
102
  ## How to run in `llama.cpp`
103
 
104
- I use the following command line; adjust for your tastes and needs:
 
 
105
 
106
  ```
107
- ./main -t 10 -ngl 32 -m chronos-beluga-v2-13b.ggmlv3.q4_K_M.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"
108
  ```
109
  Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.
110
 
@@ -118,9 +136,10 @@ For other parameters and how to use them, please refer to [the llama.cpp documen
118
 
119
  ## How to run in `text-generation-webui`
120
 
121
- Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
122
 
123
  <!-- footer start -->
 
124
  ## Discord
125
 
126
  For further support, and discussions on these models and AI in general, join us at:
@@ -140,13 +159,15 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
140
  * Patreon: https://patreon.com/TheBlokeAI
141
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
142
 
143
- **Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
144
 
145
- **Patreon special mentions**: Willem Michiel, Ajan Kanaga, Cory Kujawski, Alps Aficionado, Nikolai Manek, Jonathan Leane, Stanislav Ovsiannikov, Michael Levine, Luke Pendergrass, Sid, K, Gabriel Tamborski, Clay Pascal, Kalila, William Sang, Will Dee, Pieter, Nathan LeClaire, ya boyyy, David Flickinger, vamX, Derek Yates, Fen Risland, Jeffrey Morgan, webtim, Daniel P. Andersen, Chadd, Edmond Seymore, Pyrater, Olusegun Samson, Lone Striker, biorpg, alfie_i, Mano Prime, Chris Smitley, Dave, zynix, Trenton Dambrowitz, Johann-Peter Hartmann, Magnesian, Spencer Kim, John Detwiler, Iucharbius, Gabriel Puliatti, LangChain4j, Luke @flexchar, Vadim, Rishabh Srivastava, Preetika Verma, Ai Maven, Femi Adebogun, WelcomeToTheClub, Leonard Tan, Imad Khwaja, Steven Wood, Stefan Sabev, Sebastain Graf, usrbinkat, Dan Guido, Sam, Eugene Pentland, Mandus, transmissions 11, Slarti, Karl Bernard, Spiking Neurons AB, Artur Olbinski, Joseph William Delisle, ReadyPlayerEmma, Olakabola, Asp the Wyvern, Space Cruiser, Matthew Berman, Randy H, subjectnull, danny, John Villwock, Illia Dulskyi, Rainer Wilmers, theTransient, Pierre Kircher, Alexandros Triantafyllidis, Viktor Bowallius, terasurfer, Deep Realms, SuperWojo, senxiiz, Oscar Rangel, Alex, Stephen Murray, Talal Aujan, Raven Klaugh, Sean Connelly, Raymond Fosdick, Fred von Graf, chris gileta, Junyu Yang, Elle
146
 
147
 
148
  Thank you to all my generous patrons and donaters!
149
 
 
 
150
  <!-- footer end -->
151
 
152
  # Original model card: Caleb Morgan's Chronos Beluga v2 13B
 
1
  ---
2
  inference: false
3
+ license: llama2
4
  model_creator: Caleb Morgan
5
  model_link: https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16
6
  model_name: Chronos Beluga v2 13B
 
9
  ---
10
 
11
  <!-- header start -->
12
+ <!-- 200823 -->
13
+ <div style="width: auto; margin-left: auto; margin-right: auto">
14
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
  </div>
16
  <div style="display: flex; justify-content: space-between; width: 100%;">
17
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
18
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
19
  </div>
20
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
21
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
22
  </div>
23
  </div>
24
+ <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
25
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
26
  <!-- header end -->
27
 
28
  # Chronos Beluga v2 13B - GGML
 
33
 
34
  This repo contains GGML format model files for [Caleb Morgan's Chronos Beluga v2 13B](https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16).
35
 
36
+ ### Important note regarding GGML files.
37
+
38
+ The GGML format has now been superseded by GGUF. As of August 21st 2023, [llama.cpp](https://github.com/ggerganov/llama.cpp) no longer supports GGML models. Third party clients and libraries are expected to still support it for a time, but many may also drop support.
39
+
40
+ Please use the GGUF models instead.
41
+ ### About GGML
42
+
43
  GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
44
  * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Supports NVidia CUDA GPU acceleration.
45
  * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a powerful GGML web UI with GPU acceleration on all platforms (CUDA and OpenCL). Especially good for story telling.
 
51
  ## Repositories available
52
 
53
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GPTQ)
54
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGUF)
55
+ * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML)
56
  * [Caleb Morgan's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/The-Face-Of-Goonery/Chronos-Beluga-v2-13bfp16)
57
 
58
  ## Prompt template: Alpaca
 
64
  {prompt}
65
 
66
  ### Response:
67
+
68
  ```
69
 
70
  <!-- compatibility_ggml start -->
71
  ## Compatibility
72
 
73
+ These quantised GGML files are compatible with llama.cpp between June 6th (commit `2d43387`) and August 21st 2023.
74
+
75
+ For support with latest llama.cpp, please use GGUF files instead.
76
 
77
+ The final llama.cpp commit with support for GGML was: [dadbed99e65252d79f81101a392d0d6497b86caa](https://github.com/ggerganov/llama.cpp/commit/dadbed99e65252d79f81101a392d0d6497b86caa)
78
+
79
+ As of August 23rd 2023 they are still compatible with all UIs, libraries and utilities which use GGML. This may change in the future.
80
 
81
  ## Explanation of the new k-quant methods
82
  <details>
 
99
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
100
  | ---- | ---- | ---- | ---- | ---- | ----- |
101
  | [chronos-beluga-v2-13b.ggmlv3.q2_K.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q2_K.bin) | q2_K | 2 | 5.51 GB| 8.01 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
 
 
102
  | [chronos-beluga-v2-13b.ggmlv3.q3_K_S.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q3_K_S.bin) | q3_K_S | 3 | 5.66 GB| 8.16 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
103
+ | [chronos-beluga-v2-13b.ggmlv3.q3_K_M.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q3_K_M.bin) | q3_K_M | 3 | 6.31 GB| 8.81 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
104
+ | [chronos-beluga-v2-13b.ggmlv3.q3_K_L.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q3_K_L.bin) | q3_K_L | 3 | 6.93 GB| 9.43 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
105
  | [chronos-beluga-v2-13b.ggmlv3.q4_0.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q4_0.bin) | q4_0 | 4 | 7.37 GB| 9.87 GB | Original quant method, 4-bit. |
 
 
106
  | [chronos-beluga-v2-13b.ggmlv3.q4_K_S.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q4_K_S.bin) | q4_K_S | 4 | 7.37 GB| 9.87 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
107
+ | [chronos-beluga-v2-13b.ggmlv3.q4_K_M.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q4_K_M.bin) | q4_K_M | 4 | 7.87 GB| 10.37 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
108
+ | [chronos-beluga-v2-13b.ggmlv3.q4_1.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q4_1.bin) | q4_1 | 4 | 8.17 GB| 10.67 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
109
  | [chronos-beluga-v2-13b.ggmlv3.q5_0.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q5_0.bin) | q5_0 | 5 | 8.97 GB| 11.47 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
 
 
110
  | [chronos-beluga-v2-13b.ggmlv3.q5_K_S.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q5_K_S.bin) | q5_K_S | 5 | 8.97 GB| 11.47 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
111
+ | [chronos-beluga-v2-13b.ggmlv3.q5_K_M.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q5_K_M.bin) | q5_K_M | 5 | 9.23 GB| 11.73 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
112
+ | [chronos-beluga-v2-13b.ggmlv3.q5_1.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q5_1.bin) | q5_1 | 5 | 9.78 GB| 12.28 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
113
  | [chronos-beluga-v2-13b.ggmlv3.q6_K.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q6_K.bin) | q6_K | 6 | 10.68 GB| 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K for all tensors - 6-bit quantization |
114
  | [chronos-beluga-v2-13b.ggmlv3.q8_0.bin](https://huggingface.co/TheBloke/Chronos-Beluga-v2-13B-GGML/blob/main/chronos-beluga-v2-13b.ggmlv3.q8_0.bin) | q8_0 | 8 | 13.79 GB| 16.29 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
115
 
 
117
 
118
  ## How to run in `llama.cpp`
119
 
120
+ Make sure you are using `llama.cpp` from commit [dadbed99e65252d79f81101a392d0d6497b86caa](https://github.com/ggerganov/llama.cpp/commit/dadbed99e65252d79f81101a392d0d6497b86caa) or earlier.
121
+
122
+ For compatibility with latest llama.cpp, please use GGUF files instead.
123
 
124
  ```
125
+ ./main -t 10 -ngl 32 -m chronos-beluga-v2-13b.ggmlv3.q4_K_M.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nWrite a story about llamas\n\n### Response:"
126
  ```
127
  Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.
128
 
 
136
 
137
  ## How to run in `text-generation-webui`
138
 
139
+ Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
140
 
141
  <!-- footer start -->
142
+ <!-- 200823 -->
143
  ## Discord
144
 
145
  For further support, and discussions on these models and AI in general, join us at:
 
159
  * Patreon: https://patreon.com/TheBlokeAI
160
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
161
 
162
+ **Special thanks to**: Aemon Algiz.
163
 
164
+ **Patreon special mentions**: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser
165
 
166
 
167
  Thank you to all my generous patrons and donaters!
168
 
169
+ And thank you again to a16z for their generous grant.
170
+
171
  <!-- footer end -->
172
 
173
  # Original model card: Caleb Morgan's Chronos Beluga v2 13B