eric-musa commited on
Commit
f6d9ef2
1 Parent(s): d98d586

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +237 -0
README.md ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3.1-8B
3
+ language:
4
+ - en
5
+ - de
6
+ - fr
7
+ - it
8
+ - pt
9
+ - hi
10
+ - es
11
+ - th
12
+ library_name: transformers
13
+ license: llama3.1
14
+ pipeline_tag: text-generation
15
+ tags:
16
+ - facebook
17
+ - meta
18
+ - pytorch
19
+ - llama
20
+ - llama-3
21
+ - llama-cpp
22
+ - gguf-my-repo
23
+ extra_gated_prompt: "### LLAMA 3.1 COMMUNITY LICENSE AGREEMENT\nLlama 3.1 Version\
24
+ \ Release Date: July 23, 2024\n\"Agreement\" means the terms and conditions for\
25
+ \ use, reproduction, distribution and modification of the Llama Materials set forth\
26
+ \ herein.\n\"Documentation\" means the specifications, manuals and documentation\
27
+ \ accompanying Llama 3.1 distributed by Meta at https://llama.meta.com/doc/overview.\n\
28
+ \"Licensee\" or \"you\" means you, or your employer or any other person or entity\
29
+ \ (if you are entering into this Agreement on such person or entity’s behalf), of\
30
+ \ the age required under applicable laws, rules or regulations to provide legal\
31
+ \ consent and that has legal authority to bind your employer or such other person\
32
+ \ or entity if you are entering in this Agreement on their behalf.\n\"Llama 3.1\"\
33
+ \ means the foundational large language models and software and algorithms, including\
34
+ \ machine-learning model code, trained model weights, inference-enabling code, training-enabling\
35
+ \ code, fine-tuning enabling code and other elements of the foregoing distributed\
36
+ \ by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means,\
37
+ \ collectively, Meta’s proprietary Llama 3.1 and Documentation (and any portion\
38
+ \ thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms\
39
+ \ Ireland Limited (if you are located in or, if you are an entity, your principal\
40
+ \ place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you\
41
+ \ are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\n\
42
+ a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable\
43
+ \ and royalty-free limited license under Meta’s intellectual property or other rights\
44
+ \ owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy,\
45
+ \ create derivative works of, and make modifications to the Llama Materials.\nb.\
46
+ \ Redistribution and Use.\ni. If you distribute or make available the Llama Materials\
47
+ \ (or any derivative works thereof), or a product or service (including another\
48
+ \ AI model) that contains any of them, you shall (A) provide a copy of this Agreement\
49
+ \ with any such Llama Materials; and (B) prominently display “Built with Llama”\
50
+ \ on a related website, user interface, blogpost, about page, or product documentation.\
51
+ \ If you use the Llama Materials or any outputs or results of the Llama Materials\
52
+ \ to create, train, fine tune, or otherwise improve an AI model, which is distributed\
53
+ \ or made available, you shall also include “Llama” at the beginning of any such\
54
+ \ AI model name.\nii. If you receive Llama Materials, or any derivative works thereof,\
55
+ \ from a Licensee as part of an integrated end user product, then Section 2 of\
56
+ \ this Agreement will not apply to you.\niii. You must retain in all copies of the\
57
+ \ Llama Materials that you distribute the following attribution notice within a\
58
+ \ “Notice” text file distributed as a part of such copies: “Llama 3.1 is licensed\
59
+ \ under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights\
60
+ \ Reserved.”\niv. Your use of the Llama Materials must comply with applicable laws\
61
+ \ and regulations (including trade compliance laws and regulations) and adhere to\
62
+ \ the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3_1/use-policy),\
63
+ \ which is hereby incorporated by reference into this Agreement.\n2. Additional\
64
+ \ Commercial Terms. If, on the Llama 3.1 version release date, the monthly active\
65
+ \ users of the products or services made available by or for Licensee, or Licensee’s\
66
+ \ affiliates, is greater than 700 million monthly active users in the preceding\
67
+ \ calendar month, you must request a license from Meta, which Meta may grant to\
68
+ \ you in its sole discretion, and you are not authorized to exercise any of the\
69
+ \ rights under this Agreement unless or until Meta otherwise expressly grants you\
70
+ \ such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE\
71
+ \ LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS”\
72
+ \ BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY\
73
+ \ KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\
74
+ \ OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.\
75
+ \ YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING\
76
+ \ THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA\
77
+ \ MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT\
78
+ \ WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN\
79
+ \ CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS\
80
+ \ AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,\
81
+ \ EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED\
82
+ \ OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No\
83
+ \ trademark licenses are granted under this Agreement, and in connection with the\
84
+ \ Llama Materials, neither Meta nor Licensee may use any name or mark owned by or\
85
+ \ associated with the other or any of its affiliates, except as required for reasonable\
86
+ \ and customary use in describing and redistributing the Llama Materials or as set\
87
+ \ forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the\
88
+ \ “Mark”) solely as required to comply with the last sentence of Section 1.b.i.\
89
+ \ You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/\
90
+ \ ). All goodwill arising out of your use of the Mark will inure to the benefit\
91
+ \ of Meta.\nb. Subject to Meta’s ownership of Llama Materials and derivatives made\
92
+ \ by or for Meta, with respect to any derivative works and modifications of the\
93
+ \ Llama Materials that are made by you, as between you and Meta, you are and will\
94
+ \ be the owner of such derivative works and modifications.\nc. If you institute\
95
+ \ litigation or other proceedings against Meta or any entity (including a cross-claim\
96
+ \ or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.1 outputs\
97
+ \ or results, or any portion of any of the foregoing, constitutes infringement of\
98
+ \ intellectual property or other rights owned or licensable by you, then any licenses\
99
+ \ granted to you under this Agreement shall terminate as of the date such litigation\
100
+ \ or claim is filed or instituted. You will indemnify and hold harmless Meta from\
101
+ \ and against any claim by any third party arising out of or related to your use\
102
+ \ or distribution of the Llama Materials.\n6. Term and Termination. The term of\
103
+ \ this Agreement will commence upon your acceptance of this Agreement or access\
104
+ \ to the Llama Materials and will continue in full force and effect until terminated\
105
+ \ in accordance with the terms and conditions herein. Meta may terminate this Agreement\
106
+ \ if you are in breach of any term or condition of this Agreement. Upon termination\
107
+ \ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
108
+ \ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
109
+ \ and Jurisdiction. This Agreement will be governed and construed under the laws\
110
+ \ of the State of California without regard to choice of law principles, and the\
111
+ \ UN Convention on Contracts for the International Sale of Goods does not apply\
112
+ \ to this Agreement. The courts of California shall have exclusive jurisdiction\
113
+ \ of any dispute arising out of this Agreement.\n### Llama 3.1 Acceptable Use Policy\n\
114
+ Meta is committed to promoting safe and fair use of its tools and features, including\
115
+ \ Llama 3.1. If you access or use Llama 3.1, you agree to this Acceptable Use Policy\
116
+ \ (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3_1/use-policy](https://llama.meta.com/llama3_1/use-policy)\n\
117
+ #### Prohibited Uses\nWe want everyone to use Llama 3.1 safely and responsibly.\
118
+ \ You agree you will not use, or allow others to use, Llama 3.1 to:\n 1. Violate\
119
+ \ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
120
+ \ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
121
+ \ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
122
+ \ or harm to children, including the solicitation, creation, acquisition, or dissemination\
123
+ \ of child exploitative content or failure to report Child Sexual Abuse Material\n\
124
+ \ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
125
+ \ illegal distribution of information or materials to minors, including obscene\
126
+ \ materials, or failure to employ legally required age-gating in connection with\
127
+ \ such information or materials.\n 5. Sexual solicitation\n 6. Any\
128
+ \ other criminal activity\n 3. Engage in, promote, incite, or facilitate the\
129
+ \ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
130
+ \ 4. Engage in, promote, incite, or facilitate discrimination or other unlawful\
131
+ \ or harmful conduct in the provision of employment, employment benefits, credit,\
132
+ \ housing, other economic benefits, or other essential goods and services\n 5.\
133
+ \ Engage in the unauthorized or unlicensed practice of any profession including,\
134
+ \ but not limited to, financial, legal, medical/health, or related professional\
135
+ \ practices\n 6. Collect, process, disclose, generate, or infer health, demographic,\
136
+ \ or other sensitive personal or private information about individuals without rights\
137
+ \ and consents required by applicable laws\n 7. Engage in or facilitate any action\
138
+ \ or generate any content that infringes, misappropriates, or otherwise violates\
139
+ \ any third-party rights, including the outputs or results of any products or services\
140
+ \ using the Llama Materials\n 8. Create, generate, or facilitate the creation\
141
+ \ of malicious code, malware, computer viruses or do anything else that could disable,\
142
+ \ overburden, interfere with or impair the proper working, integrity, operation\
143
+ \ or appearance of a website or computer system\n2. Engage in, promote, incite,\
144
+ \ facilitate, or assist in the planning or development of activities that present\
145
+ \ a risk of death or bodily harm to individuals, including use of Llama 3.1 related\
146
+ \ to the following:\n 1. Military, warfare, nuclear industries or applications,\
147
+ \ espionage, use for materials or activities that are subject to the International\
148
+ \ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
149
+ \ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
150
+ \ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
151
+ \ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
152
+ \ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
153
+ \ content intended to incite or promote violence, abuse, or any infliction of bodily\
154
+ \ harm to an individual\n3. Intentionally deceive or mislead others, including use\
155
+ \ of Llama 3.1 related to the following:\n 1. Generating, promoting, or furthering\
156
+ \ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
157
+ \ or furthering defamatory content, including the creation of defamatory statements,\
158
+ \ images, or other content\n 3. Generating, promoting, or further distributing\
159
+ \ spam\n 4. Impersonating another individual without consent, authorization,\
160
+ \ or legal right\n 5. Representing that the use of Llama 3.1 or outputs are human-generated\n\
161
+ \ 6. Generating or facilitating false online engagement, including fake reviews\
162
+ \ and other means of fake online engagement\n4. Fail to appropriately disclose to\
163
+ \ end users any known dangers of your AI system\nPlease report any violation of\
164
+ \ this Policy, software “bug,” or other problems that could lead to a violation\
165
+ \ of this Policy through one of the following means:\n * Reporting issues with\
166
+ \ the model: [https://github.com/meta-llama/llama-models/issues](https://github.com/meta-llama/llama-models/issues)\n\
167
+ \ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
168
+ \ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
169
+ \ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]"
170
+ extra_gated_fields:
171
+ First Name: text
172
+ Last Name: text
173
+ Date of birth: date_picker
174
+ Country: country
175
+ Affiliation: text
176
+ Job title:
177
+ type: select
178
+ options:
179
+ - Student
180
+ - Research Graduate
181
+ - AI researcher
182
+ - AI developer/engineer
183
+ - Reporter
184
+ - Other
185
+ geo: ip_location
186
+ ? By clicking Submit below I accept the terms of the license and acknowledge that
187
+ the information I provide will be collected stored processed and shared in accordance
188
+ with the Meta Privacy Policy
189
+ : checkbox
190
+ extra_gated_description: The information you provide will be collected, stored, processed
191
+ and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
192
+ extra_gated_button_content: Submit
193
+ ---
194
+
195
+ # eric-musa/Meta-Llama-3.1-8B-Q4_K_M-GGUF
196
+ This model was converted to GGUF format from [`meta-llama/Meta-Llama-3.1-8B`](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
197
+ Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) for more details on the model.
198
+
199
+ ## Use with llama.cpp
200
+ Install llama.cpp through brew (works on Mac and Linux)
201
+
202
+ ```bash
203
+ brew install llama.cpp
204
+
205
+ ```
206
+ Invoke the llama.cpp server or the CLI.
207
+
208
+ ### CLI:
209
+ ```bash
210
+ llama-cli --hf-repo eric-musa/Meta-Llama-3.1-8B-Q4_K_M-GGUF --hf-file meta-llama-3.1-8b-q4_k_m.gguf -p "The meaning to life and the universe is"
211
+ ```
212
+
213
+ ### Server:
214
+ ```bash
215
+ llama-server --hf-repo eric-musa/Meta-Llama-3.1-8B-Q4_K_M-GGUF --hf-file meta-llama-3.1-8b-q4_k_m.gguf -c 2048
216
+ ```
217
+
218
+ 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.
219
+
220
+ Step 1: Clone llama.cpp from GitHub.
221
+ ```
222
+ git clone https://github.com/ggerganov/llama.cpp
223
+ ```
224
+
225
+ 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).
226
+ ```
227
+ cd llama.cpp && LLAMA_CURL=1 make
228
+ ```
229
+
230
+ Step 3: Run inference through the main binary.
231
+ ```
232
+ ./llama-cli --hf-repo eric-musa/Meta-Llama-3.1-8B-Q4_K_M-GGUF --hf-file meta-llama-3.1-8b-q4_k_m.gguf -p "The meaning to life and the universe is"
233
+ ```
234
+ or
235
+ ```
236
+ ./llama-server --hf-repo eric-musa/Meta-Llama-3.1-8B-Q4_K_M-GGUF --hf-file meta-llama-3.1-8b-q4_k_m.gguf -c 2048
237
+ ```