yuliu1234 commited on
Commit
f8ddd47
1 Parent(s): 08fcf71

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +248 -0
README.md ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: llama3
5
+ tags:
6
+ - facebook
7
+ - meta
8
+ - pytorch
9
+ - llama
10
+ - llama-3
11
+ - llama-cpp
12
+ - gguf-my-repo
13
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
14
+ pipeline_tag: text-generation
15
+ extra_gated_prompt: "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version\
16
+ \ Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for\
17
+ \ use, reproduction, distribution and modification of the Llama Materials set forth\
18
+ \ herein.\n\"Documentation\" means the specifications, manuals and documentation\
19
+ \ accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\
20
+ \"Licensee\" or \"you\" means you, or your employer or any other person or entity\
21
+ \ (if you are entering into this Agreement on such person or entity’s behalf), of\
22
+ \ the age required under applicable laws, rules or regulations to provide legal\
23
+ \ consent and that has legal authority to bind your employer or such other person\
24
+ \ or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama\
25
+ \ 3\" means the foundational large language models and software and algorithms,\
26
+ \ including machine-learning model code, trained model weights, inference-enabling\
27
+ \ code, training-enabling code, fine-tuning enabling code and other elements of\
28
+ \ the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\
29
+ \"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation\
30
+ \ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"\
31
+ we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\
32
+ \ an entity, your principal place of business is in the EEA or Switzerland) and\
33
+ \ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n\
34
+ \ \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted\
35
+ \ a non-exclusive, worldwide, non-transferable and royalty-free limited license\
36
+ \ under Meta’s intellectual property or other rights owned by Meta embodied in the\
37
+ \ Llama Materials to use, reproduce, distribute, copy, create derivative works of,\
38
+ \ and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni.\
39
+ \ If you distribute or make available the Llama Materials (or any derivative works\
40
+ \ thereof), or a product or service that uses any of them, including another AI\
41
+ \ model, you shall (A) provide a copy of this Agreement with any such Llama Materials;\
42
+ \ and (B) prominently display “Built with Meta Llama 3” on a related website, user\
43
+ \ interface, blogpost, about page, or product documentation. If you use the Llama\
44
+ \ Materials to create, train, fine tune, or otherwise improve an AI model, which\
45
+ \ is distributed or made available, you shall also include “Llama 3” at the beginning\
46
+ \ of any such AI model name.\nii. If you receive Llama Materials, or any derivative\
47
+ \ works thereof, from a Licensee as part of an integrated end user product, then\
48
+ \ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\
49
+ \ copies of the Llama Materials that you distribute the following attribution notice\
50
+ \ within a “Notice” text file distributed as a part of such copies: “Meta Llama\
51
+ \ 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms,\
52
+ \ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
53
+ \ applicable laws and regulations (including trade compliance laws and regulations)\
54
+ \ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
55
+ \ https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference\
56
+ \ into this Agreement.\nv. You will not use the Llama Materials or any output or\
57
+ \ results of the Llama Materials to improve any other large language model (excluding\
58
+ \ Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If,\
59
+ \ on the Meta Llama 3 version release date, the monthly active users of the products\
60
+ \ or services made available by or for Licensee, or Licensee’s affiliates, is greater\
61
+ \ than 700 million monthly active users in the preceding calendar month, you must\
62
+ \ request a license from Meta, which Meta may grant to you in its sole discretion,\
63
+ \ and you are not authorized to exercise any of the rights under this Agreement\
64
+ \ unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer\
65
+ \ of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT\
66
+ \ AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\
67
+ \ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\
68
+ \ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\
69
+ \ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\
70
+ \ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\
71
+ \ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\
72
+ 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\
73
+ \ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\
74
+ \ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\
75
+ \ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\
76
+ \ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\
77
+ 5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\
78
+ \ and in connection with the Llama Materials, neither Meta nor Licensee may use\
79
+ \ any name or mark owned by or associated with the other or any of its affiliates,\
80
+ \ except as required for reasonable and customary use in describing and redistributing\
81
+ \ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\
82
+ \ a license to use “Llama 3” (the “Mark”) solely as required to comply with the\
83
+ \ last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently\
84
+ \ accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All\
85
+ \ goodwill arising out of your use of the Mark will inure to the benefit of Meta.\n\
86
+ b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for\
87
+ \ Meta, with respect to any derivative works and modifications of the Llama Materials\
88
+ \ that are made by you, as between you and Meta, you are and will be the owner of\
89
+ \ such derivative works and modifications.\nc. If you institute litigation or other\
90
+ \ proceedings against Meta or any entity (including a cross-claim or counterclaim\
91
+ \ in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results,\
92
+ \ or any portion of any of the foregoing, constitutes infringement of intellectual\
93
+ \ property or other rights owned or licensable by you, then any licenses granted\
94
+ \ to you under this Agreement shall terminate as of the date such litigation or\
95
+ \ claim is filed or instituted. You will indemnify and hold harmless Meta from and\
96
+ \ against any claim by any third party arising out of or related to your use or\
97
+ \ distribution of the Llama Materials.\n6. Term and Termination. The term of this\
98
+ \ Agreement will commence upon your acceptance of this Agreement or access to the\
99
+ \ Llama Materials and will continue in full force and effect until terminated in\
100
+ \ accordance with the terms and conditions herein. Meta may terminate this Agreement\
101
+ \ if you are in breach of any term or condition of this Agreement. Upon termination\
102
+ \ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
103
+ \ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
104
+ \ and Jurisdiction. This Agreement will be governed and construed under the laws\
105
+ \ of the State of California without regard to choice of law principles, and the\
106
+ \ UN Convention on Contracts for the International Sale of Goods does not apply\
107
+ \ to this Agreement. The courts of California shall have exclusive jurisdiction\
108
+ \ of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use\
109
+ \ Policy\nMeta is committed to promoting safe and fair use of its tools and features,\
110
+ \ including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable\
111
+ \ Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n\
112
+ #### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly.\
113
+ \ You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate\
114
+ \ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
115
+ \ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
116
+ \ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
117
+ \ or harm to children, including the solicitation, creation, acquisition, or dissemination\
118
+ \ of child exploitative content or failure to report Child Sexual Abuse Material\n\
119
+ \ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
120
+ \ illegal distribution of information or materials to minors, including obscene\
121
+ \ materials, or failure to employ legally required age-gating in connection with\
122
+ \ such information or materials.\n 5. Sexual solicitation\n 6. Any\
123
+ \ other criminal activity\n 2. Engage in, promote, incite, or facilitate the\
124
+ \ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
125
+ \ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\
126
+ \ or harmful conduct in the provision of employment, employment benefits, credit,\
127
+ \ housing, other economic benefits, or other essential goods and services\n 4.\
128
+ \ Engage in the unauthorized or unlicensed practice of any profession including,\
129
+ \ but not limited to, financial, legal, medical/health, or related professional\
130
+ \ practices\n 5. Collect, process, disclose, generate, or infer health, demographic,\
131
+ \ or other sensitive personal or private information about individuals without rights\
132
+ \ and consents required by applicable laws\n 6. Engage in or facilitate any action\
133
+ \ or generate any content that infringes, misappropriates, or otherwise violates\
134
+ \ any third-party rights, including the outputs or results of any products or services\
135
+ \ using the Llama Materials\n 7. Create, generate, or facilitate the creation\
136
+ \ of malicious code, malware, computer viruses or do anything else that could disable,\
137
+ \ overburden, interfere with or impair the proper working, integrity, operation\
138
+ \ or appearance of a website or computer system\n2. Engage in, promote, incite,\
139
+ \ facilitate, or assist in the planning or development of activities that present\
140
+ \ a risk of death or bodily harm to individuals, including use of Meta Llama 3 related\
141
+ \ to the following:\n 1. Military, warfare, nuclear industries or applications,\
142
+ \ espionage, use for materials or activities that are subject to the International\
143
+ \ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
144
+ \ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
145
+ \ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
146
+ \ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
147
+ \ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
148
+ \ content intended to incite or promote violence, abuse, or any infliction of bodily\
149
+ \ harm to an individual\n3. Intentionally deceive or mislead others, including use\
150
+ \ of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering\
151
+ \ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
152
+ \ or furthering defamatory content, including the creation of defamatory statements,\
153
+ \ images, or other content\n 3. Generating, promoting, or further distributing\
154
+ \ spam\n 4. Impersonating another individual without consent, authorization,\
155
+ \ or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are\
156
+ \ human-generated\n 6. Generating or facilitating false online engagement, including\
157
+ \ fake reviews and other means of fake online engagement\n4. Fail to appropriately\
158
+ \ disclose to end users any known dangers of your AI system\nPlease report any violation\
159
+ \ of this Policy, software “bug,” or other problems that could lead to a violation\
160
+ \ of this Policy through one of the following means:\n * Reporting issues with\
161
+ \ the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n\
162
+ \ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
163
+ \ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
164
+ \ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: LlamaUseReport@meta.com"
165
+ extra_gated_fields:
166
+ First Name: text
167
+ Last Name: text
168
+ Date of birth: date_picker
169
+ Country: country
170
+ Affiliation: text
171
+ geo: ip_location
172
+ ? By clicking Submit below I accept the terms of the license and acknowledge that
173
+ the information I provide will be collected stored processed and shared in accordance
174
+ with the Meta Privacy Policy
175
+ : checkbox
176
+ extra_gated_description: The information you provide will be collected, stored, processed
177
+ and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
178
+ extra_gated_button_content: Submit
179
+ widget:
180
+ - example_title: Hello
181
+ messages:
182
+ - role: user
183
+ content: Hey my name is Julien! How are you?
184
+ - example_title: Winter holidays
185
+ messages:
186
+ - role: system
187
+ content: You are a helpful and honest assistant. Please, respond concisely and
188
+ truthfully.
189
+ - role: user
190
+ content: Can you recommend a good destination for Winter holidays?
191
+ - example_title: Programming assistant
192
+ messages:
193
+ - role: system
194
+ content: You are a helpful and honest code and programming assistant. Please,
195
+ respond concisely and truthfully.
196
+ - role: user
197
+ content: Write a function that computes the nth fibonacci number.
198
+ inference:
199
+ parameters:
200
+ max_new_tokens: 300
201
+ stop:
202
+ - <|end_of_text|>
203
+ - <|eot_id|>
204
+ ---
205
+
206
+ # yuliu1234/Meta-Llama-3-8B-Instruct-Q8_0-GGUF
207
+ This model was converted to GGUF format from [`meta-llama/Meta-Llama-3-8B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
208
+ Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) for more details on the model.
209
+
210
+ ## Use with llama.cpp
211
+ Install llama.cpp through brew (works on Mac and Linux)
212
+
213
+ ```bash
214
+ brew install llama.cpp
215
+
216
+ ```
217
+ Invoke the llama.cpp server or the CLI.
218
+
219
+ ### CLI:
220
+ ```bash
221
+ llama --hf-repo yuliu1234/Meta-Llama-3-8B-Instruct-Q8_0-GGUF --hf-file meta-llama-3-8b-instruct-q8_0.gguf -p "The meaning to life and the universe is"
222
+ ```
223
+
224
+ ### Server:
225
+ ```bash
226
+ llama-server --hf-repo yuliu1234/Meta-Llama-3-8B-Instruct-Q8_0-GGUF --hf-file meta-llama-3-8b-instruct-q8_0.gguf -c 2048
227
+ ```
228
+
229
+ Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
230
+
231
+ Step 1: Clone llama.cpp from GitHub.
232
+ ```
233
+ git clone https://github.com/ggerganov/llama.cpp
234
+ ```
235
+
236
+ Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
237
+ ```
238
+ cd llama.cpp && LLAMA_CURL=1 make
239
+ ```
240
+
241
+ Step 3: Run inference through the main binary.
242
+ ```
243
+ ./main --hf-repo yuliu1234/Meta-Llama-3-8B-Instruct-Q8_0-GGUF --hf-file meta-llama-3-8b-instruct-q8_0.gguf -p "The meaning to life and the universe is"
244
+ ```
245
+ or
246
+ ```
247
+ ./server --hf-repo yuliu1234/Meta-Llama-3-8B-Instruct-Q8_0-GGUF --hf-file meta-llama-3-8b-instruct-q8_0.gguf -c 2048
248
+ ```