Text Generation
Transformers
PyTorch
English
llama
llama-2
qCammel-13
TheBloke commited on
Commit
6cda0f2
1 Parent(s): 6c00c7e

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +40 -22
README.md CHANGED
@@ -3,7 +3,7 @@ inference: false
3
  language:
4
  - en
5
  library_name: transformers
6
- license: other
7
  model_creator: augtoma
8
  model_link: https://huggingface.co/augtoma/qCammel-13
9
  model_name: qCammel 13
@@ -18,17 +18,20 @@ tags:
18
  ---
19
 
20
  <!-- header start -->
21
- <div style="width: 100%;">
22
- <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
 
23
  </div>
24
  <div style="display: flex; justify-content: space-between; width: 100%;">
25
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
26
- <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
27
  </div>
28
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
29
- <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
30
  </div>
31
  </div>
 
 
32
  <!-- header end -->
33
 
34
  # qCammel 13 - GGML
@@ -39,6 +42,13 @@ tags:
39
 
40
  This repo contains GGML format model files for [augtoma's qCammel 13](https://huggingface.co/augtoma/qCammel-13).
41
 
 
 
 
 
 
 
 
42
  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:
43
  * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Supports NVidia CUDA GPU acceleration.
44
  * [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.
@@ -50,24 +60,27 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
50
  ## Repositories available
51
 
52
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/qCammel-13-GPTQ)
53
- * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/qCammel-13-GGML)
 
54
  * [augtoma's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/augtoma/qCammel-13)
55
 
56
  ## Prompt template: Vicuna
57
 
58
  ```
59
- A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
60
 
61
- USER: {prompt}
62
- ASSISTANT:
63
  ```
64
 
65
  <!-- compatibility_ggml start -->
66
  ## Compatibility
67
 
68
- These quantised GGML files are compatible with llama.cpp as of June 6th, commit `2d43387`.
 
 
 
 
69
 
70
- They should also be compatible with all UIs, libraries and utilities which use GGML.
71
 
72
  ## Explanation of the new k-quant methods
73
  <details>
@@ -90,17 +103,17 @@ Refer to the Provided Files table below to see what files use which methods, and
90
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
91
  | ---- | ---- | ---- | ---- | ---- | ----- |
92
  | [qcammel-13.ggmlv3.q2_K.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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. |
93
- | [qcammel-13.ggmlv3.q3_K_L.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
94
- | [qcammel-13.ggmlv3.q3_K_M.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
95
  | [qcammel-13.ggmlv3.q3_K_S.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
 
 
96
  | [qcammel-13.ggmlv3.q4_0.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.ggmlv3.q4_0.bin) | q4_0 | 4 | 7.37 GB| 9.87 GB | Original quant method, 4-bit. |
97
- | [qcammel-13.ggmlv3.q4_1.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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. |
98
- | [qcammel-13.ggmlv3.q4_K_M.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
99
  | [qcammel-13.ggmlv3.q4_K_S.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
 
 
100
  | [qcammel-13.ggmlv3.q5_0.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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. |
101
- | [qcammel-13.ggmlv3.q5_1.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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. |
102
- | [qcammel-13.ggmlv3.q5_K_M.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
103
  | [qcammel-13.ggmlv3.q5_K_S.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
 
 
104
  | [qcammel-13.ggmlv3.q6_K.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
105
  | [qcammel-13.ggmlv3.q8_0.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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. |
106
 
@@ -108,10 +121,12 @@ Refer to the Provided Files table below to see what files use which methods, and
108
 
109
  ## How to run in `llama.cpp`
110
 
111
- I use the following command line; adjust for your tastes and needs:
 
 
112
 
113
  ```
114
- ./main -t 10 -ngl 32 -m qcammel-13.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:"
115
  ```
116
  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`.
117
 
@@ -125,9 +140,10 @@ For other parameters and how to use them, please refer to [the llama.cpp documen
125
 
126
  ## How to run in `text-generation-webui`
127
 
128
- 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).
129
 
130
  <!-- footer start -->
 
131
  ## Discord
132
 
133
  For further support, and discussions on these models and AI in general, join us at:
@@ -147,13 +163,15 @@ Donaters will get priority support on any and all AI/LLM/model questions and req
147
  * Patreon: https://patreon.com/TheBlokeAI
148
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
149
 
150
- **Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
151
 
152
- **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
153
 
154
 
155
  Thank you to all my generous patrons and donaters!
156
 
 
 
157
  <!-- footer end -->
158
 
159
  # Original model card: augtoma's qCammel 13
 
3
  language:
4
  - en
5
  library_name: transformers
6
+ license: llama2
7
  model_creator: augtoma
8
  model_link: https://huggingface.co/augtoma/qCammel-13
9
  model_name: qCammel 13
 
18
  ---
19
 
20
  <!-- header start -->
21
+ <!-- 200823 -->
22
+ <div style="width: auto; margin-left: auto; margin-right: auto">
23
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
24
  </div>
25
  <div style="display: flex; justify-content: space-between; width: 100%;">
26
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
27
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
28
  </div>
29
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
30
+ <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>
31
  </div>
32
  </div>
33
+ <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>
34
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
35
  <!-- header end -->
36
 
37
  # qCammel 13 - GGML
 
42
 
43
  This repo contains GGML format model files for [augtoma's qCammel 13](https://huggingface.co/augtoma/qCammel-13).
44
 
45
+ ### Important note regarding GGML files.
46
+
47
+ 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.
48
+
49
+ Please use the GGUF models instead.
50
+ ### About GGML
51
+
52
  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:
53
  * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Supports NVidia CUDA GPU acceleration.
54
  * [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.
 
60
  ## Repositories available
61
 
62
  * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/qCammel-13-GPTQ)
63
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/qCammel-13-GGUF)
64
+ * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/qCammel-13-GGML)
65
  * [augtoma's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/augtoma/qCammel-13)
66
 
67
  ## Prompt template: Vicuna
68
 
69
  ```
70
+ A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
71
 
 
 
72
  ```
73
 
74
  <!-- compatibility_ggml start -->
75
  ## Compatibility
76
 
77
+ These quantised GGML files are compatible with llama.cpp between June 6th (commit `2d43387`) and August 21st 2023.
78
+
79
+ For support with latest llama.cpp, please use GGUF files instead.
80
+
81
+ The final llama.cpp commit with support for GGML was: [dadbed99e65252d79f81101a392d0d6497b86caa](https://github.com/ggerganov/llama.cpp/commit/dadbed99e65252d79f81101a392d0d6497b86caa)
82
 
83
+ As of August 23rd 2023 they are still compatible with all UIs, libraries and utilities which use GGML. This may change in the future.
84
 
85
  ## Explanation of the new k-quant methods
86
  <details>
 
103
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
104
  | ---- | ---- | ---- | ---- | ---- | ----- |
105
  | [qcammel-13.ggmlv3.q2_K.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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. |
 
 
106
  | [qcammel-13.ggmlv3.q3_K_S.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
107
+ | [qcammel-13.ggmlv3.q3_K_M.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
108
+ | [qcammel-13.ggmlv3.q3_K_L.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
109
  | [qcammel-13.ggmlv3.q4_0.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.ggmlv3.q4_0.bin) | q4_0 | 4 | 7.37 GB| 9.87 GB | Original quant method, 4-bit. |
 
 
110
  | [qcammel-13.ggmlv3.q4_K_S.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
111
+ | [qcammel-13.ggmlv3.q4_K_M.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
112
+ | [qcammel-13.ggmlv3.q4_1.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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. |
113
  | [qcammel-13.ggmlv3.q5_0.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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. |
 
 
114
  | [qcammel-13.ggmlv3.q5_K_S.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
115
+ | [qcammel-13.ggmlv3.q5_K_M.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
116
+ | [qcammel-13.ggmlv3.q5_1.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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. |
117
  | [qcammel-13.ggmlv3.q6_K.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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 |
118
  | [qcammel-13.ggmlv3.q8_0.bin](https://huggingface.co/TheBloke/qCammel-13-GGML/blob/main/qcammel-13.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. |
119
 
 
121
 
122
  ## How to run in `llama.cpp`
123
 
124
+ Make sure you are using `llama.cpp` from commit [dadbed99e65252d79f81101a392d0d6497b86caa](https://github.com/ggerganov/llama.cpp/commit/dadbed99e65252d79f81101a392d0d6497b86caa) or earlier.
125
+
126
+ For compatibility with latest llama.cpp, please use GGUF files instead.
127
 
128
  ```
129
+ ./main -t 10 -ngl 32 -m qcammel-13.ggmlv3.q4_K_M.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Write a story about llamas ASSISTANT:"
130
  ```
131
  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`.
132
 
 
140
 
141
  ## How to run in `text-generation-webui`
142
 
143
+ Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
144
 
145
  <!-- footer start -->
146
+ <!-- 200823 -->
147
  ## Discord
148
 
149
  For further support, and discussions on these models and AI in general, join us at:
 
163
  * Patreon: https://patreon.com/TheBlokeAI
164
  * Ko-Fi: https://ko-fi.com/TheBlokeAI
165
 
166
+ **Special thanks to**: Aemon Algiz.
167
 
168
+ **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
169
 
170
 
171
  Thank you to all my generous patrons and donaters!
172
 
173
+ And thank you again to a16z for their generous grant.
174
+
175
  <!-- footer end -->
176
 
177
  # Original model card: augtoma's qCammel 13