Trisert commited on
Commit
4871601
1 Parent(s): 8408fe0

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +236 -0
README.md ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
3
+ language:
4
+ - en
5
+ - de
6
+ - fr
7
+ - it
8
+ - pt
9
+ - hi
10
+ - es
11
+ - th
12
+ license: llama3.1
13
+ pipeline_tag: text-generation
14
+ tags:
15
+ - facebook
16
+ - meta
17
+ - pytorch
18
+ - llama
19
+ - llama-3
20
+ - llama-cpp
21
+ - gguf-my-repo
22
+ extra_gated_prompt: "### LLAMA 3.1 COMMUNITY LICENSE AGREEMENT\nLlama 3.1 Version\
23
+ \ Release Date: July 23, 2024\n\"Agreement\" means the terms and conditions for\
24
+ \ use, reproduction, distribution and modification of the Llama Materials set forth\
25
+ \ herein.\n\"Documentation\" means the specifications, manuals and documentation\
26
+ \ accompanying Llama 3.1 distributed by Meta at https://llama.meta.com/doc/overview.\n\
27
+ \"Licensee\" or \"you\" means you, or your employer or any other person or entity\
28
+ \ (if you are entering into this Agreement on such person or entity’s behalf), of\
29
+ \ the age required under applicable laws, rules or regulations to provide legal\
30
+ \ consent and that has legal authority to bind your employer or such other person\
31
+ \ or entity if you are entering in this Agreement on their behalf.\n\"Llama 3.1\"\
32
+ \ means the foundational large language models and software and algorithms, including\
33
+ \ machine-learning model code, trained model weights, inference-enabling code, training-enabling\
34
+ \ code, fine-tuning enabling code and other elements of the foregoing distributed\
35
+ \ by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means,\
36
+ \ collectively, Meta’s proprietary Llama 3.1 and Documentation (and any portion\
37
+ \ thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms\
38
+ \ Ireland Limited (if you are located in or, if you are an entity, your principal\
39
+ \ place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you\
40
+ \ are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\n\
41
+ a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable\
42
+ \ and royalty-free limited license under Meta’s intellectual property or other rights\
43
+ \ owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy,\
44
+ \ create derivative works of, and make modifications to the Llama Materials.\nb.\
45
+ \ Redistribution and Use.\ni. If you distribute or make available the Llama Materials\
46
+ \ (or any derivative works thereof), or a product or service (including another\
47
+ \ AI model) that contains any of them, you shall (A) provide a copy of this Agreement\
48
+ \ with any such Llama Materials; and (B) prominently display “Built with Llama”\
49
+ \ on a related website, user interface, blogpost, about page, or product documentation.\
50
+ \ If you use the Llama Materials or any outputs or results of the Llama Materials\
51
+ \ to create, train, fine tune, or otherwise improve an AI model, which is distributed\
52
+ \ or made available, you shall also include “Llama” at the beginning of any such\
53
+ \ AI model name.\nii. If you receive Llama Materials, or any derivative works thereof,\
54
+ \ from a Licensee as part of an integrated end user product, then Section 2 of\
55
+ \ this Agreement will not apply to you.\niii. You must retain in all copies of the\
56
+ \ Llama Materials that you distribute the following attribution notice within a\
57
+ \ “Notice” text file distributed as a part of such copies: “Llama 3.1 is licensed\
58
+ \ under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights\
59
+ \ Reserved.”\niv. Your use of the Llama Materials must comply with applicable laws\
60
+ \ and regulations (including trade compliance laws and regulations) and adhere to\
61
+ \ the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3_1/use-policy),\
62
+ \ which is hereby incorporated by reference into this Agreement.\n2. Additional\
63
+ \ Commercial Terms. If, on the Llama 3.1 version release date, the monthly active\
64
+ \ users of the products or services made available by or for Licensee, or Licensee’s\
65
+ \ affiliates, is greater than 700 million monthly active users in the preceding\
66
+ \ calendar month, you must request a license from Meta, which Meta may grant to\
67
+ \ you in its sole discretion, and you are not authorized to exercise any of the\
68
+ \ rights under this Agreement unless or until Meta otherwise expressly grants you\
69
+ \ such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE\
70
+ \ LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS”\
71
+ \ BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY\
72
+ \ KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\
73
+ \ OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.\
74
+ \ YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING\
75
+ \ THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA\
76
+ \ MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT\
77
+ \ WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN\
78
+ \ CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS\
79
+ \ AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,\
80
+ \ EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED\
81
+ \ OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No\
82
+ \ trademark licenses are granted under this Agreement, and in connection with the\
83
+ \ Llama Materials, neither Meta nor Licensee may use any name or mark owned by or\
84
+ \ associated with the other or any of its affiliates, except as required for reasonable\
85
+ \ and customary use in describing and redistributing the Llama Materials or as set\
86
+ \ forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the\
87
+ \ “Mark”) solely as required to comply with the last sentence of Section 1.b.i.\
88
+ \ You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/\
89
+ \ ). All goodwill arising out of your use of the Mark will inure to the benefit\
90
+ \ of Meta.\nb. Subject to Meta’s ownership of Llama Materials and derivatives made\
91
+ \ by or for Meta, with respect to any derivative works and modifications of the\
92
+ \ Llama Materials that are made by you, as between you and Meta, you are and will\
93
+ \ be the owner of such derivative works and modifications.\nc. If you institute\
94
+ \ litigation or other proceedings against Meta or any entity (including a cross-claim\
95
+ \ or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.1 outputs\
96
+ \ or results, or any portion of any of the foregoing, constitutes infringement of\
97
+ \ intellectual property or other rights owned or licensable by you, then any licenses\
98
+ \ granted to you under this Agreement shall terminate as of the date such litigation\
99
+ \ or claim is filed or instituted. You will indemnify and hold harmless Meta from\
100
+ \ and against any claim by any third party arising out of or related to your use\
101
+ \ or distribution of the Llama Materials.\n6. Term and Termination. The term of\
102
+ \ this Agreement will commence upon your acceptance of this Agreement or access\
103
+ \ to the Llama Materials and will continue in full force and effect until terminated\
104
+ \ in accordance with the terms and conditions herein. Meta may terminate this Agreement\
105
+ \ if you are in breach of any term or condition of this Agreement. Upon termination\
106
+ \ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
107
+ \ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
108
+ \ and Jurisdiction. This Agreement will be governed and construed under the laws\
109
+ \ of the State of California without regard to choice of law principles, and the\
110
+ \ UN Convention on Contracts for the International Sale of Goods does not apply\
111
+ \ to this Agreement. The courts of California shall have exclusive jurisdiction\
112
+ \ of any dispute arising out of this Agreement.\n### Llama 3.1 Acceptable Use Policy\n\
113
+ Meta is committed to promoting safe and fair use of its tools and features, including\
114
+ \ Llama 3.1. If you access or use Llama 3.1, you agree to this Acceptable Use Policy\
115
+ \ (“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\
116
+ #### Prohibited Uses\nWe want everyone to use Llama 3.1 safely and responsibly.\
117
+ \ You agree you will not use, or allow others to use, Llama 3.1 to:\n 1. Violate\
118
+ \ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
119
+ \ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
120
+ \ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
121
+ \ or harm to children, including the solicitation, creation, acquisition, or dissemination\
122
+ \ of child exploitative content or failure to report Child Sexual Abuse Material\n\
123
+ \ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
124
+ \ illegal distribution of information or materials to minors, including obscene\
125
+ \ materials, or failure to employ legally required age-gating in connection with\
126
+ \ such information or materials.\n 5. Sexual solicitation\n 6. Any\
127
+ \ other criminal activity\n 3. Engage in, promote, incite, or facilitate the\
128
+ \ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
129
+ \ 4. Engage in, promote, incite, or facilitate discrimination or other unlawful\
130
+ \ or harmful conduct in the provision of employment, employment benefits, credit,\
131
+ \ housing, other economic benefits, or other essential goods and services\n 5.\
132
+ \ Engage in the unauthorized or unlicensed practice of any profession including,\
133
+ \ but not limited to, financial, legal, medical/health, or related professional\
134
+ \ practices\n 6. Collect, process, disclose, generate, or infer health, demographic,\
135
+ \ or other sensitive personal or private information about individuals without rights\
136
+ \ and consents required by applicable laws\n 7. Engage in or facilitate any action\
137
+ \ or generate any content that infringes, misappropriates, or otherwise violates\
138
+ \ any third-party rights, including the outputs or results of any products or services\
139
+ \ using the Llama Materials\n 8. Create, generate, or facilitate the creation\
140
+ \ of malicious code, malware, computer viruses or do anything else that could disable,\
141
+ \ overburden, interfere with or impair the proper working, integrity, operation\
142
+ \ or appearance of a website or computer system\n2. Engage in, promote, incite,\
143
+ \ facilitate, or assist in the planning or development of activities that present\
144
+ \ a risk of death or bodily harm to individuals, including use of Llama 3.1 related\
145
+ \ to the following:\n 1. Military, warfare, nuclear industries or applications,\
146
+ \ espionage, use for materials or activities that are subject to the International\
147
+ \ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
148
+ \ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
149
+ \ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
150
+ \ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
151
+ \ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
152
+ \ content intended to incite or promote violence, abuse, or any infliction of bodily\
153
+ \ harm to an individual\n3. Intentionally deceive or mislead others, including use\
154
+ \ of Llama 3.1 related to the following:\n 1. Generating, promoting, or furthering\
155
+ \ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
156
+ \ or furthering defamatory content, including the creation of defamatory statements,\
157
+ \ images, or other content\n 3. Generating, promoting, or further distributing\
158
+ \ spam\n 4. Impersonating another individual without consent, authorization,\
159
+ \ or legal right\n 5. Representing that the use of Llama 3.1 or outputs are human-generated\n\
160
+ \ 6. Generating or facilitating false online engagement, including fake reviews\
161
+ \ and other means of fake online engagement\n4. Fail to appropriately disclose to\
162
+ \ end users any known dangers of your AI system\nPlease report any violation of\
163
+ \ this Policy, software “bug,” or other problems that could lead to a violation\
164
+ \ of this Policy through one of the following means:\n * Reporting issues with\
165
+ \ the model: [https://github.com/meta-llama/llama-models/issues](https://github.com/meta-llama/llama-models/issues)\n\
166
+ \ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
167
+ \ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
168
+ \ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]"
169
+ extra_gated_fields:
170
+ First Name: text
171
+ Last Name: text
172
+ Date of birth: date_picker
173
+ Country: country
174
+ Affiliation: text
175
+ Job title:
176
+ type: select
177
+ options:
178
+ - Student
179
+ - Research Graduate
180
+ - AI researcher
181
+ - AI developer/engineer
182
+ - Reporter
183
+ - Other
184
+ geo: ip_location
185
+ ? By clicking Submit below I accept the terms of the license and acknowledge that
186
+ the information I provide will be collected stored processed and shared in accordance
187
+ with the Meta Privacy Policy
188
+ : checkbox
189
+ extra_gated_description: The information you provide will be collected, stored, processed
190
+ and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
191
+ extra_gated_button_content: Submit
192
+ ---
193
+
194
+ # Trisert/Meta-Llama-3.1-8B-Instruct-IQ4_NL-GGUF
195
+ This model was converted to GGUF format from [`meta-llama/Meta-Llama-3.1-8B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
196
+ Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) for more details on the model.
197
+
198
+ ## Use with llama.cpp
199
+ Install llama.cpp through brew (works on Mac and Linux)
200
+
201
+ ```bash
202
+ brew install llama.cpp
203
+
204
+ ```
205
+ Invoke the llama.cpp server or the CLI.
206
+
207
+ ### CLI:
208
+ ```bash
209
+ llama-cli --hf-repo Trisert/Meta-Llama-3.1-8B-Instruct-IQ4_NL-GGUF --hf-file meta-llama-3.1-8b-instruct-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
210
+ ```
211
+
212
+ ### Server:
213
+ ```bash
214
+ llama-server --hf-repo Trisert/Meta-Llama-3.1-8B-Instruct-IQ4_NL-GGUF --hf-file meta-llama-3.1-8b-instruct-iq4_nl-imat.gguf -c 2048
215
+ ```
216
+
217
+ 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.
218
+
219
+ Step 1: Clone llama.cpp from GitHub.
220
+ ```
221
+ git clone https://github.com/ggerganov/llama.cpp
222
+ ```
223
+
224
+ 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).
225
+ ```
226
+ cd llama.cpp && LLAMA_CURL=1 make
227
+ ```
228
+
229
+ Step 3: Run inference through the main binary.
230
+ ```
231
+ ./llama-cli --hf-repo Trisert/Meta-Llama-3.1-8B-Instruct-IQ4_NL-GGUF --hf-file meta-llama-3.1-8b-instruct-iq4_nl-imat.gguf -p "The meaning to life and the universe is"
232
+ ```
233
+ or
234
+ ```
235
+ ./llama-server --hf-repo Trisert/Meta-Llama-3.1-8B-Instruct-IQ4_NL-GGUF --hf-file meta-llama-3.1-8b-instruct-iq4_nl-imat.gguf -c 2048
236
+ ```