TheBloke commited on
Commit
77d2558
1 Parent(s): ff88f9d

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +493 -0
README.md ADDED
@@ -0,0 +1,493 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: FelixChao/vicuna-33b-coder
3
+ inference: false
4
+ license: other
5
+ model-index:
6
+ - name: Vicuna-Coder
7
+ results:
8
+ - dataset:
9
+ name: MultiPL-HumanEval (Python)
10
+ type: nuprl/MultiPL-E
11
+ metrics:
12
+ - name: pass@1
13
+ type: pass@1
14
+ value: 0.274
15
+ verified: false
16
+ task:
17
+ type: text-generation
18
+ model_creator: Chao Chang-Yu
19
+ model_name: Vicuna 33B Coder
20
+ model_type: llama
21
+ prompt_template: 'A chat between a curious user and an artificial intelligence assistant.
22
+ The assistant gives helpful, detailed, and polite answers to the user''s questions.
23
+ USER: {prompt} ASSISTANT:
24
+
25
+ '
26
+ quantized_by: TheBloke
27
+ tags:
28
+ - code
29
+ ---
30
+
31
+ <!-- header start -->
32
+ <!-- 200823 -->
33
+ <div style="width: auto; margin-left: auto; margin-right: auto">
34
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
35
+ </div>
36
+ <div style="display: flex; justify-content: space-between; width: 100%;">
37
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
38
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
39
+ </div>
40
+ <div style="display: flex; flex-direction: column; align-items: flex-end;">
41
+ <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>
42
+ </div>
43
+ </div>
44
+ <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>
45
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
46
+ <!-- header end -->
47
+
48
+ # Vicuna 33B Coder - GGUF
49
+ - Model creator: [Chao Chang-Yu](https://huggingface.co/FelixChao)
50
+ - Original model: [Vicuna 33B Coder](https://huggingface.co/FelixChao/vicuna-33b-coder)
51
+
52
+ <!-- description start -->
53
+ ## Description
54
+
55
+ This repo contains GGUF format model files for [Chao Chang-Yu's Vicuna 33B Coder](https://huggingface.co/FelixChao/vicuna-33b-coder).
56
+
57
+ <!-- description end -->
58
+ <!-- README_GGUF.md-about-gguf start -->
59
+ ### About GGUF
60
+
61
+ GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
62
+
63
+ Here is an incomplate list of clients and libraries that are known to support GGUF:
64
+
65
+ * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
66
+ * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
67
+ * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
68
+ * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
69
+ * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
70
+ * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
71
+ * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
72
+ * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
73
+ * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
74
+
75
+ <!-- README_GGUF.md-about-gguf end -->
76
+ <!-- repositories-available start -->
77
+ ## Repositories available
78
+
79
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/vicuna-33B-coder-AWQ)
80
+ * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/vicuna-33B-coder-GPTQ)
81
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF)
82
+ * [Chao Chang-Yu's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/FelixChao/vicuna-33b-coder)
83
+ <!-- repositories-available end -->
84
+
85
+ <!-- prompt-template start -->
86
+ ## Prompt template: Vicuna
87
+
88
+ ```
89
+ 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:
90
+
91
+ ```
92
+
93
+ <!-- prompt-template end -->
94
+
95
+
96
+ <!-- compatibility_gguf start -->
97
+ ## Compatibility
98
+
99
+ These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
100
+
101
+ They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
102
+
103
+ ## Explanation of quantisation methods
104
+ <details>
105
+ <summary>Click to see details</summary>
106
+
107
+ The new methods available are:
108
+ * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
109
+ * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
110
+ * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
111
+ * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
112
+ * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
113
+
114
+ Refer to the Provided Files table below to see what files use which methods, and how.
115
+ </details>
116
+ <!-- compatibility_gguf end -->
117
+
118
+ <!-- README_GGUF.md-provided-files start -->
119
+ ## Provided files
120
+
121
+ | Name | Quant method | Bits | Size | Max RAM required | Use case |
122
+ | ---- | ---- | ---- | ---- | ---- | ----- |
123
+ | [vicuna-33b-coder.Q2_K.gguf](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF/blob/main/vicuna-33b-coder.Q2_K.gguf) | Q2_K | 2 | 13.50 GB| 16.00 GB | smallest, significant quality loss - not recommended for most purposes |
124
+ | [vicuna-33b-coder.Q3_K_S.gguf](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF/blob/main/vicuna-33b-coder.Q3_K_S.gguf) | Q3_K_S | 3 | 14.06 GB| 16.56 GB | very small, high quality loss |
125
+ | [vicuna-33b-coder.Q3_K_M.gguf](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF/blob/main/vicuna-33b-coder.Q3_K_M.gguf) | Q3_K_M | 3 | 15.76 GB| 18.26 GB | very small, high quality loss |
126
+ | [vicuna-33b-coder.Q3_K_L.gguf](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF/blob/main/vicuna-33b-coder.Q3_K_L.gguf) | Q3_K_L | 3 | 17.28 GB| 19.78 GB | small, substantial quality loss |
127
+ | [vicuna-33b-coder.Q4_0.gguf](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF/blob/main/vicuna-33b-coder.Q4_0.gguf) | Q4_0 | 4 | 18.36 GB| 20.86 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
128
+ | [vicuna-33b-coder.Q4_K_S.gguf](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF/blob/main/vicuna-33b-coder.Q4_K_S.gguf) | Q4_K_S | 4 | 18.44 GB| 20.94 GB | small, greater quality loss |
129
+ | [vicuna-33b-coder.Q4_K_M.gguf](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF/blob/main/vicuna-33b-coder.Q4_K_M.gguf) | Q4_K_M | 4 | 19.62 GB| 22.12 GB | medium, balanced quality - recommended |
130
+ | [vicuna-33b-coder.Q5_0.gguf](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF/blob/main/vicuna-33b-coder.Q5_0.gguf) | Q5_0 | 5 | 22.40 GB| 24.90 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
131
+ | [vicuna-33b-coder.Q5_K_S.gguf](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF/blob/main/vicuna-33b-coder.Q5_K_S.gguf) | Q5_K_S | 5 | 22.40 GB| 24.90 GB | large, low quality loss - recommended |
132
+ | [vicuna-33b-coder.Q5_K_M.gguf](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF/blob/main/vicuna-33b-coder.Q5_K_M.gguf) | Q5_K_M | 5 | 23.05 GB| 25.55 GB | large, very low quality loss - recommended |
133
+ | [vicuna-33b-coder.Q6_K.gguf](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF/blob/main/vicuna-33b-coder.Q6_K.gguf) | Q6_K | 6 | 26.69 GB| 29.19 GB | very large, extremely low quality loss |
134
+ | [vicuna-33b-coder.Q8_0.gguf](https://huggingface.co/TheBloke/vicuna-33B-coder-GGUF/blob/main/vicuna-33b-coder.Q8_0.gguf) | Q8_0 | 8 | 34.57 GB| 37.07 GB | very large, extremely low quality loss - not recommended |
135
+
136
+ **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
137
+
138
+
139
+
140
+ <!-- README_GGUF.md-provided-files end -->
141
+
142
+ <!-- README_GGUF.md-how-to-download start -->
143
+ ## How to download GGUF files
144
+
145
+ **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
146
+
147
+ The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
148
+ - LM Studio
149
+ - LoLLMS Web UI
150
+ - Faraday.dev
151
+
152
+ ### In `text-generation-webui`
153
+
154
+ Under Download Model, you can enter the model repo: TheBloke/vicuna-33B-coder-GGUF and below it, a specific filename to download, such as: vicuna-33b-coder.Q4_K_M.gguf.
155
+
156
+ Then click Download.
157
+
158
+ ### On the command line, including multiple files at once
159
+
160
+ I recommend using the `huggingface-hub` Python library:
161
+
162
+ ```shell
163
+ pip3 install huggingface-hub
164
+ ```
165
+
166
+ Then you can download any individual model file to the current directory, at high speed, with a command like this:
167
+
168
+ ```shell
169
+ huggingface-cli download TheBloke/vicuna-33B-coder-GGUF vicuna-33b-coder.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
170
+ ```
171
+
172
+ <details>
173
+ <summary>More advanced huggingface-cli download usage</summary>
174
+
175
+ You can also download multiple files at once with a pattern:
176
+
177
+ ```shell
178
+ huggingface-cli download TheBloke/vicuna-33B-coder-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
179
+ ```
180
+
181
+ For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
182
+
183
+ To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
184
+
185
+ ```shell
186
+ pip3 install hf_transfer
187
+ ```
188
+
189
+ And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
190
+
191
+ ```shell
192
+ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/vicuna-33B-coder-GGUF vicuna-33b-coder.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
193
+ ```
194
+
195
+ Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
196
+ </details>
197
+ <!-- README_GGUF.md-how-to-download end -->
198
+
199
+ <!-- README_GGUF.md-how-to-run start -->
200
+ ## Example `llama.cpp` command
201
+
202
+ Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
203
+
204
+ ```shell
205
+ ./main -ngl 32 -m vicuna-33b-coder.Q4_K_M.gguf --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: {prompt} ASSISTANT:"
206
+ ```
207
+
208
+ Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
209
+
210
+ Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
211
+
212
+ If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
213
+
214
+ For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
215
+
216
+ ## How to run in `text-generation-webui`
217
+
218
+ Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
219
+
220
+ ## How to run from Python code
221
+
222
+ You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.
223
+
224
+ ### How to load this model in Python code, using ctransformers
225
+
226
+ #### First install the package
227
+
228
+ Run one of the following commands, according to your system:
229
+
230
+ ```shell
231
+ # Base ctransformers with no GPU acceleration
232
+ pip install ctransformers
233
+ # Or with CUDA GPU acceleration
234
+ pip install ctransformers[cuda]
235
+ # Or with AMD ROCm GPU acceleration (Linux only)
236
+ CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
237
+ # Or with Metal GPU acceleration for macOS systems only
238
+ CT_METAL=1 pip install ctransformers --no-binary ctransformers
239
+ ```
240
+
241
+ #### Simple ctransformers example code
242
+
243
+ ```python
244
+ from ctransformers import AutoModelForCausalLM
245
+
246
+ # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
247
+ llm = AutoModelForCausalLM.from_pretrained("TheBloke/vicuna-33B-coder-GGUF", model_file="vicuna-33b-coder.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
248
+
249
+ print(llm("AI is going to"))
250
+ ```
251
+
252
+ ## How to use with LangChain
253
+
254
+ Here are guides on using llama-cpp-python and ctransformers with LangChain:
255
+
256
+ * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
257
+ * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
258
+
259
+ <!-- README_GGUF.md-how-to-run end -->
260
+
261
+ <!-- footer start -->
262
+ <!-- 200823 -->
263
+ ## Discord
264
+
265
+ For further support, and discussions on these models and AI in general, join us at:
266
+
267
+ [TheBloke AI's Discord server](https://discord.gg/theblokeai)
268
+
269
+ ## Thanks, and how to contribute
270
+
271
+ Thanks to the [chirper.ai](https://chirper.ai) team!
272
+
273
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
274
+
275
+ 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.
276
+
277
+ 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.
278
+
279
+ Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
280
+
281
+ * Patreon: https://patreon.com/TheBlokeAI
282
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
283
+
284
+ **Special thanks to**: Aemon Algiz.
285
+
286
+ **Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
287
+
288
+
289
+ Thank you to all my generous patrons and donaters!
290
+
291
+ And thank you again to a16z for their generous grant.
292
+
293
+ <!-- footer end -->
294
+
295
+ <!-- original-model-card start -->
296
+ # Original model card: Chao Chang-Yu's Vicuna 33B Coder
297
+
298
+ ---
299
+ # Model Card for Model ID
300
+
301
+ <!-- Provide a quick summary of what the model is/does. -->
302
+
303
+ This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
304
+
305
+ ## Model Details
306
+
307
+ ### Model Description
308
+
309
+ <!-- Provide a longer summary of what this model is. -->
310
+
311
+
312
+
313
+ - **Developed by:** [More Information Needed]
314
+ - **Shared by [optional]:** [More Information Needed]
315
+ - **Model type:** [More Information Needed]
316
+ - **Language(s) (NLP):** [More Information Needed]
317
+ - **License:** [More Information Needed]
318
+ - **Finetuned from model [optional]:** [More Information Needed]
319
+
320
+ ### Model Sources [optional]
321
+
322
+ <!-- Provide the basic links for the model. -->
323
+
324
+ - **Repository:** [More Information Needed]
325
+ - **Paper [optional]:** [More Information Needed]
326
+ - **Demo [optional]:** [More Information Needed]
327
+
328
+ ## Uses
329
+
330
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
331
+
332
+ ### Direct Use
333
+
334
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
335
+
336
+ [More Information Needed]
337
+
338
+ ### Downstream Use [optional]
339
+
340
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
341
+
342
+ [More Information Needed]
343
+
344
+ ### Out-of-Scope Use
345
+
346
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
347
+
348
+ [More Information Needed]
349
+
350
+ ## Bias, Risks, and Limitations
351
+
352
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
353
+
354
+ [More Information Needed]
355
+
356
+ ### Recommendations
357
+
358
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
359
+
360
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
361
+
362
+ ## How to Get Started with the Model
363
+
364
+ Use the code below to get started with the model.
365
+
366
+ [More Information Needed]
367
+
368
+ ## Training Details
369
+
370
+ ### Training Data
371
+
372
+ <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
373
+
374
+ [More Information Needed]
375
+
376
+ ### Training Procedure
377
+
378
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
379
+
380
+ #### Preprocessing [optional]
381
+
382
+ [More Information Needed]
383
+
384
+
385
+ #### Training Hyperparameters
386
+
387
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
388
+
389
+ #### Speeds, Sizes, Times [optional]
390
+
391
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
392
+
393
+ [More Information Needed]
394
+
395
+ ## Evaluation
396
+
397
+ <!-- This section describes the evaluation protocols and provides the results. -->
398
+
399
+ ### Testing Data, Factors & Metrics
400
+
401
+ #### Testing Data
402
+
403
+ <!-- This should link to a Data Card if possible. -->
404
+
405
+ [More Information Needed]
406
+
407
+ #### Factors
408
+
409
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
410
+
411
+ [More Information Needed]
412
+
413
+ #### Metrics
414
+
415
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
416
+
417
+ [More Information Needed]
418
+
419
+ ### Results
420
+
421
+ [More Information Needed]
422
+
423
+ #### Summary
424
+
425
+
426
+
427
+ ## Model Examination [optional]
428
+
429
+ <!-- Relevant interpretability work for the model goes here -->
430
+
431
+ [More Information Needed]
432
+
433
+ ## Environmental Impact
434
+
435
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
436
+
437
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
438
+
439
+ - **Hardware Type:** [More Information Needed]
440
+ - **Hours used:** [More Information Needed]
441
+ - **Cloud Provider:** [More Information Needed]
442
+ - **Compute Region:** [More Information Needed]
443
+ - **Carbon Emitted:** [More Information Needed]
444
+
445
+ ## Technical Specifications [optional]
446
+
447
+ ### Model Architecture and Objective
448
+
449
+ [More Information Needed]
450
+
451
+ ### Compute Infrastructure
452
+
453
+ [More Information Needed]
454
+
455
+ #### Hardware
456
+
457
+ [More Information Needed]
458
+
459
+ #### Software
460
+
461
+ [More Information Needed]
462
+
463
+ ## Citation [optional]
464
+
465
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
466
+
467
+ **BibTeX:**
468
+
469
+ [More Information Needed]
470
+
471
+ **APA:**
472
+
473
+ [More Information Needed]
474
+
475
+ ## Glossary [optional]
476
+
477
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
478
+
479
+ [More Information Needed]
480
+
481
+ ## More Information [optional]
482
+
483
+ [More Information Needed]
484
+
485
+ ## Model Card Authors [optional]
486
+
487
+ [More Information Needed]
488
+
489
+ ## Model Card Contact
490
+
491
+ [More Information Needed]
492
+
493
+ <!-- original-model-card end -->