TheBloke commited on
Commit
4cf013f
1 Parent(s): 2652e40

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +382 -0
README.md ADDED
@@ -0,0 +1,382 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: OpenBuddy/openbuddy-mixtral-7bx8-v16.3-32k
3
+ inference: false
4
+ language:
5
+ - zh
6
+ - en
7
+ - fr
8
+ - de
9
+ - ja
10
+ - ko
11
+ - it
12
+ - ru
13
+ library_name: transformers
14
+ license: apache-2.0
15
+ model_creator: OpenBuddy
16
+ model_name: Openbuddy Mixtral 7Bx8 V16.3 32K
17
+ model_type: mixtral
18
+ pipeline_tag: text-generation
19
+ prompt_template: "You are a helpful, respectful and honest INTP-T AI Assistant named\
20
+ \ Buddy. You are talking to a human User.\nAlways answer as helpfully and logically\
21
+ \ as possible, while being safe. Your answers should not include any harmful, political,\
22
+ \ religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please\
23
+ \ ensure that your responses are socially unbiased and positive in nature.\nIf a\
24
+ \ question does not make any sense, or is not factually coherent, explain why instead\
25
+ \ of answering something not correct. If you don't know the answer to a question,\
26
+ \ please don't share false information.\nYou like to use emojis. You can speak fluently\
27
+ \ in many languages, for example: English, Chinese.\nYou cannot access the internet,\
28
+ \ but you have vast knowledge, cutoff: 2021-09.\nYou are trained by OpenBuddy team,\
29
+ \ (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), you are based\
30
+ \ on LLaMA and Falcon transformers model, not related to GPT or OpenAI.\n\nUser:\
31
+ \ {prompt}\nAssistant: \n"
32
+ quantized_by: TheBloke
33
+ ---
34
+ <!-- markdownlint-disable MD041 -->
35
+
36
+ <!-- header start -->
37
+ <!-- 200823 -->
38
+ <div style="width: auto; margin-left: auto; margin-right: auto">
39
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
40
+ </div>
41
+ <div style="display: flex; justify-content: space-between; width: 100%;">
42
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
43
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
44
+ </div>
45
+ <div style="display: flex; flex-direction: column; align-items: flex-end;">
46
+ <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>
47
+ </div>
48
+ </div>
49
+ <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>
50
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
51
+ <!-- header end -->
52
+
53
+ # Openbuddy Mixtral 7Bx8 V16.3 32K - GGUF
54
+ - Model creator: [OpenBuddy](https://huggingface.co/OpenBuddy)
55
+ - Original model: [Openbuddy Mixtral 7Bx8 V16.3 32K](https://huggingface.co/OpenBuddy/openbuddy-mixtral-7bx8-v16.3-32k)
56
+
57
+ <!-- description start -->
58
+ ## Description
59
+
60
+ This repo contains GGUF format model files for [OpenBuddy's Openbuddy Mixtral 7Bx8 V16.3 32K](https://huggingface.co/OpenBuddy/openbuddy-mixtral-7bx8-v16.3-32k).
61
+
62
+ These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
63
+
64
+ <!-- description end -->
65
+ <!-- README_GGUF.md-about-gguf start -->
66
+ ### About GGUF
67
+
68
+ 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.
69
+
70
+ Here is an incomplete list of clients and libraries that are known to support GGUF:
71
+
72
+ * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
73
+ * [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.
74
+ * [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.
75
+ * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
76
+ * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
77
+ * [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.
78
+ * [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.
79
+ * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
80
+ * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
81
+ * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
82
+
83
+ <!-- README_GGUF.md-about-gguf end -->
84
+ <!-- repositories-available start -->
85
+ ## Repositories available
86
+
87
+ * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-AWQ)
88
+ * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GPTQ)
89
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF)
90
+ * [OpenBuddy's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/OpenBuddy/openbuddy-mixtral-7bx8-v16.3-32k)
91
+ <!-- repositories-available end -->
92
+
93
+ <!-- prompt-template start -->
94
+ ## Prompt template: OpenBuddy
95
+
96
+ ```
97
+ You are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human User.
98
+ Always answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
99
+ If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
100
+ You like to use emojis. You can speak fluently in many languages, for example: English, Chinese.
101
+ You cannot access the internet, but you have vast knowledge, cutoff: 2021-09.
102
+ You are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), you are based on LLaMA and Falcon transformers model, not related to GPT or OpenAI.
103
+
104
+ User: {prompt}
105
+ Assistant:
106
+
107
+ ```
108
+
109
+ <!-- prompt-template end -->
110
+
111
+
112
+ <!-- compatibility_gguf start -->
113
+ ## Compatibility
114
+
115
+ 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)
116
+
117
+ They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
118
+
119
+ ## Explanation of quantisation methods
120
+
121
+ <details>
122
+ <summary>Click to see details</summary>
123
+
124
+ The new methods available are:
125
+
126
+ * 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)
127
+ * 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.
128
+ * 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.
129
+ * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
130
+ * 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
131
+
132
+ Refer to the Provided Files table below to see what files use which methods, and how.
133
+ </details>
134
+ <!-- compatibility_gguf end -->
135
+
136
+ <!-- README_GGUF.md-provided-files start -->
137
+ ## Provided files
138
+
139
+ | Name | Quant method | Bits | Size | Max RAM required | Use case |
140
+ | ---- | ---- | ---- | ---- | ---- | ----- |
141
+ | [openbuddy-mixtral-7bx8-v16.3-32k.Q2_K.gguf](https://huggingface.co/TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF/blob/main/openbuddy-mixtral-7bx8-v16.3-32k.Q2_K.gguf) | Q2_K | 2 | 15.67 GB| 18.17 GB | smallest, significant quality loss - not recommended for most purposes |
142
+ | [openbuddy-mixtral-7bx8-v16.3-32k.Q3_K_M.gguf](https://huggingface.co/TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF/blob/main/openbuddy-mixtral-7bx8-v16.3-32k.Q3_K_M.gguf) | Q3_K_M | 3 | 20.39 GB| 22.89 GB | very small, high quality loss |
143
+ | [openbuddy-mixtral-7bx8-v16.3-32k.Q4_0.gguf](https://huggingface.co/TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF/blob/main/openbuddy-mixtral-7bx8-v16.3-32k.Q4_0.gguf) | Q4_0 | 4 | 26.47 GB| 28.97 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
144
+ | [openbuddy-mixtral-7bx8-v16.3-32k.Q4_K_M.gguf](https://huggingface.co/TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF/blob/main/openbuddy-mixtral-7bx8-v16.3-32k.Q4_K_M.gguf) | Q4_K_M | 4 | 26.47 GB| 28.97 GB | medium, balanced quality - recommended |
145
+ | [openbuddy-mixtral-7bx8-v16.3-32k.Q5_0.gguf](https://huggingface.co/TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF/blob/main/openbuddy-mixtral-7bx8-v16.3-32k.Q5_0.gguf) | Q5_0 | 5 | 32.26 GB| 34.76 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
146
+ | [openbuddy-mixtral-7bx8-v16.3-32k.Q5_K_M.gguf](https://huggingface.co/TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF/blob/main/openbuddy-mixtral-7bx8-v16.3-32k.Q5_K_M.gguf) | Q5_K_M | 5 | 32.26 GB| 34.76 GB | large, very low quality loss - recommended |
147
+ | [openbuddy-mixtral-7bx8-v16.3-32k.Q6_K.gguf](https://huggingface.co/TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF/blob/main/openbuddy-mixtral-7bx8-v16.3-32k.Q6_K.gguf) | Q6_K | 6 | 38.41 GB| 40.91 GB | very large, extremely low quality loss |
148
+ | [openbuddy-mixtral-7bx8-v16.3-32k.Q8_0.gguf](https://huggingface.co/TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF/blob/main/openbuddy-mixtral-7bx8-v16.3-32k.Q8_0.gguf) | Q8_0 | 8 | 49.67 GB| 52.17 GB | very large, extremely low quality loss - not recommended |
149
+
150
+ **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.
151
+
152
+
153
+
154
+ <!-- README_GGUF.md-provided-files end -->
155
+
156
+ <!-- README_GGUF.md-how-to-download start -->
157
+ ## How to download GGUF files
158
+
159
+ **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.
160
+
161
+ The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
162
+
163
+ * LM Studio
164
+ * LoLLMS Web UI
165
+ * Faraday.dev
166
+
167
+ ### In `text-generation-webui`
168
+
169
+ Under Download Model, you can enter the model repo: TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF and below it, a specific filename to download, such as: openbuddy-mixtral-7bx8-v16.3-32k.Q4_K_M.gguf.
170
+
171
+ Then click Download.
172
+
173
+ ### On the command line, including multiple files at once
174
+
175
+ I recommend using the `huggingface-hub` Python library:
176
+
177
+ ```shell
178
+ pip3 install huggingface-hub
179
+ ```
180
+
181
+ Then you can download any individual model file to the current directory, at high speed, with a command like this:
182
+
183
+ ```shell
184
+ huggingface-cli download TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF openbuddy-mixtral-7bx8-v16.3-32k.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
185
+ ```
186
+
187
+ <details>
188
+ <summary>More advanced huggingface-cli download usage (click to read)</summary>
189
+
190
+ You can also download multiple files at once with a pattern:
191
+
192
+ ```shell
193
+ huggingface-cli download TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
194
+ ```
195
+
196
+ 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).
197
+
198
+ To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
199
+
200
+ ```shell
201
+ pip3 install hf_transfer
202
+ ```
203
+
204
+ And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
205
+
206
+ ```shell
207
+ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF openbuddy-mixtral-7bx8-v16.3-32k.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
208
+ ```
209
+
210
+ Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
211
+ </details>
212
+ <!-- README_GGUF.md-how-to-download end -->
213
+
214
+ <!-- README_GGUF.md-how-to-run start -->
215
+ ## Example `llama.cpp` command
216
+
217
+ Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
218
+
219
+ ```shell
220
+ ./main -ngl 35 -m openbuddy-mixtral-7bx8-v16.3-32k.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human User.\nAlways answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\nYou like to use emojis. You can speak fluently in many languages, for example: English, Chinese.\nYou cannot access the internet, but you have vast knowledge, cutoff: 2021-09.\nYou are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), you are based on LLaMA and Falcon transformers model, not related to GPT or OpenAI.\n\nUser: {prompt}\nAssistant:"
221
+ ```
222
+
223
+ Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
224
+
225
+ Change `-c 32768` 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. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
226
+
227
+ If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
228
+
229
+ 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)
230
+
231
+ ## How to run in `text-generation-webui`
232
+
233
+ Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
234
+
235
+ ## How to run from Python code
236
+
237
+ 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. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
238
+
239
+ ### How to load this model in Python code, using llama-cpp-python
240
+
241
+ For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
242
+
243
+ #### First install the package
244
+
245
+ Run one of the following commands, according to your system:
246
+
247
+ ```shell
248
+ # Base ctransformers with no GPU acceleration
249
+ pip install llama-cpp-python
250
+ # With NVidia CUDA acceleration
251
+ CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
252
+ # Or with OpenBLAS acceleration
253
+ CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
254
+ # Or with CLBLast acceleration
255
+ CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
256
+ # Or with AMD ROCm GPU acceleration (Linux only)
257
+ CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
258
+ # Or with Metal GPU acceleration for macOS systems only
259
+ CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
260
+
261
+ # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
262
+ $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
263
+ pip install llama-cpp-python
264
+ ```
265
+
266
+ #### Simple llama-cpp-python example code
267
+
268
+ ```python
269
+ from llama_cpp import Llama
270
+
271
+ # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
272
+ llm = Llama(
273
+ model_path="./openbuddy-mixtral-7bx8-v16.3-32k.Q4_K_M.gguf", # Download the model file first
274
+ n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources
275
+ n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
276
+ n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
277
+ )
278
+
279
+ # Simple inference example
280
+ output = llm(
281
+ "You are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human User.\nAlways answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\nYou like to use emojis. You can speak fluently in many languages, for example: English, Chinese.\nYou cannot access the internet, but you have vast knowledge, cutoff: 2021-09.\nYou are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), you are based on LLaMA and Falcon transformers model, not related to GPT or OpenAI.\n\nUser: {prompt}\nAssistant:", # Prompt
282
+ max_tokens=512, # Generate up to 512 tokens
283
+ stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
284
+ echo=True # Whether to echo the prompt
285
+ )
286
+
287
+ # Chat Completion API
288
+
289
+ llm = Llama(model_path="./openbuddy-mixtral-7bx8-v16.3-32k.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
290
+ llm.create_chat_completion(
291
+ messages = [
292
+ {"role": "system", "content": "You are a story writing assistant."},
293
+ {
294
+ "role": "user",
295
+ "content": "Write a story about llamas."
296
+ }
297
+ ]
298
+ )
299
+ ```
300
+
301
+ ## How to use with LangChain
302
+
303
+ Here are guides on using llama-cpp-python and ctransformers with LangChain:
304
+
305
+ * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
306
+ * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
307
+
308
+ <!-- README_GGUF.md-how-to-run end -->
309
+
310
+ <!-- footer start -->
311
+ <!-- 200823 -->
312
+ ## Discord
313
+
314
+ For further support, and discussions on these models and AI in general, join us at:
315
+
316
+ [TheBloke AI's Discord server](https://discord.gg/theblokeai)
317
+
318
+ ## Thanks, and how to contribute
319
+
320
+ Thanks to the [chirper.ai](https://chirper.ai) team!
321
+
322
+ Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
323
+
324
+ 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.
325
+
326
+ 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.
327
+
328
+ Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
329
+
330
+ * Patreon: https://patreon.com/TheBlokeAI
331
+ * Ko-Fi: https://ko-fi.com/TheBlokeAI
332
+
333
+ **Special thanks to**: Aemon Algiz.
334
+
335
+ **Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
336
+
337
+
338
+ Thank you to all my generous patrons and donaters!
339
+
340
+ And thank you again to a16z for their generous grant.
341
+
342
+ <!-- footer end -->
343
+
344
+ <!-- original-model-card start -->
345
+ # Original model card: OpenBuddy's Openbuddy Mixtral 7Bx8 V16.3 32K
346
+
347
+
348
+
349
+ # OpenBuddy - Open Multilingual Chatbot
350
+
351
+ GitHub and Usage Guide: [https://github.com/OpenBuddy/OpenBuddy](https://github.com/OpenBuddy/OpenBuddy)
352
+
353
+ Website and Demo: [https://openbuddy.ai](https://openbuddy.ai)
354
+
355
+ Evaluation result of this model: [Evaluation.txt](Evaluation.txt)
356
+
357
+ ![Demo](https://raw.githubusercontent.com/OpenBuddy/OpenBuddy/main/media/demo.png)
358
+
359
+ # Copyright Notice
360
+
361
+ Base model: https://huggingface.co/mistralai/Mixtral-8x7B-v0.1
362
+
363
+ License: Apache 2.0
364
+
365
+ ## Disclaimer
366
+
367
+ All OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions.
368
+
369
+ OpenBuddy is provided "as-is" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, whether in an action of contract, tort, or otherwise, arising from, out of, or in connection with the software or the use or other dealings in the software.
370
+
371
+ By using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy.
372
+
373
+
374
+ ## 免责声明
375
+
376
+ 所有OpenBuddy模型均存在固有的局限性,可能产生错误的、有害的、冒犯性的或其他不良的输出。用户在关键或高风险场景中应谨慎行事,不要使用这些模型,以免导致人身伤害、财产损失或重大损失。此类场景的例子包括但不限于医疗领域、可能导致伤害的软硬件系统的控制以及进行重要的财务或法律决策。
377
+
378
+ OpenBuddy按“原样”提供,不附带任何种类的明示或暗示的保证,包括但不限于适销性、特定目的的适用性和非侵权的暗示保证。在任何情况下,作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任(无论是合同、侵权还是其他原因)承担责任。
379
+
380
+ 使用OpenBuddy即表示您同意这些条款和条件,并承认您了解其使用可能带来的潜在风险。您还同意赔偿并使作者、贡献者和版权所有者免受因您使用OpenBuddy而产生的任何索赔、损害赔偿或责任的影响。
381
+
382
+ <!-- original-model-card end -->