zhentaoyu commited on
Commit
7f965a8
1 Parent(s): e4de76f

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +216 -0
README.md ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: llama2
5
+ tags:
6
+ - facebook
7
+ - meta
8
+ - pytorch
9
+ - llama
10
+ - llama-2
11
+ - llama-cpp
12
+ - gguf-my-repo
13
+ base_model: meta-llama/Llama-2-7b-chat-hf
14
+ extra_gated_heading: You need to share contact information with Meta to access this
15
+ model
16
+ extra_gated_prompt: "### LLAMA 2 COMMUNITY LICENSE AGREEMENT\n\"Agreement\" means\
17
+ \ the terms and conditions for use, reproduction, distribution and modification\
18
+ \ of the Llama Materials set forth herein. \n\"Documentation\" means the specifications,\
19
+ \ manuals and documentation accompanying Llama 2 distributed by Meta at https://ai.meta.com/resources/models-and-libraries/llama-downloads/.\
20
+ \ \n\"Licensee\" or \"you\" means you, or your employer or any other person or\
21
+ \ entity (if you are entering into this Agreement on such person or entity's behalf),\
22
+ \ of 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\"Llama 2\"\
25
+ \ means the foundational large language models and software and algorithms, including\
26
+ \ machine-learning model code, trained model weights, inference-enabling code, training-enabling\
27
+ \ code, fine-tuning enabling code and other elements of the foregoing distributed\
28
+ \ by Meta at ai.meta.com/resources/models-and-libraries/llama-downloads/.\n\"Llama\
29
+ \ Materials\" means, collectively, Meta's proprietary Llama 2 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
+ \nBy clicking \"I Accept\" below or by using or distributing any portion or element\
35
+ \ of the Llama Materials, you agree to be bound by this Agreement.\n1. License Rights\
36
+ \ and Redistribution. \na. Grant of Rights. You are granted a non-exclusive, worldwide,\
37
+ \ non- transferable and royalty-free limited license under Meta's intellectual property\
38
+ \ or other rights owned by Meta embodied in the Llama Materials to use, reproduce,\
39
+ \ distribute, copy, create derivative works of, and make modifications to the Llama\
40
+ \ Materials. \nb. Redistribution and Use.\ni. If you distribute or make the Llama\
41
+ \ Materials, or any derivative works thereof, available to a third party, you shall\
42
+ \ provide a copy of this Agreement to such third party. \nii. If you receive Llama\
43
+ \ Materials, or any derivative works thereof, from a Licensee as part of an integrated\
44
+ \ end user product, then Section 2 of this Agreement will not apply to you. \n\
45
+ iii. You must retain in all copies of the Llama Materials that you distribute the\
46
+ \ following attribution notice within a \"Notice\" text file distributed as a part\
47
+ \ of such copies: \"Llama 2 is licensed under the LLAMA 2 Community License, Copyright\
48
+ \ (c) Meta Platforms, Inc. All Rights Reserved.\"\niv. Your use of the Llama Materials\
49
+ \ must comply with applicable laws and regulations (including trade compliance\
50
+ \ laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials\
51
+ \ (available at https://ai.meta.com/llama/use-policy), which is hereby incorporated\
52
+ \ by reference into this Agreement.\nv. You will not use the Llama Materials or\
53
+ \ any output or results of the Llama Materials to improve any other large language\
54
+ \ model (excluding Llama 2 or derivative works thereof). \n\n2. Additional Commercial\
55
+ \ Terms. If, on the Llama 2 version release date, the monthly active users of the\
56
+ \ products or services made available by or for Licensee, or Licensee's affiliates,\
57
+ \ is greater than 700 million monthly active users in the preceding calendar month,\
58
+ \ you must request a license from Meta, which Meta may grant to you in its sole\
59
+ \ discretion, and you are not authorized to exercise any of the rights under this\
60
+ \ Agreement unless or until Meta otherwise expressly grants you such rights.\n\
61
+ 3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS\
62
+ \ AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \"AS IS\" BASIS, WITHOUT\
63
+ \ WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION,\
64
+ \ ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A\
65
+ \ PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS\
66
+ \ OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED\
67
+ \ WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation\
68
+ \ of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY\
69
+ \ OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE,\
70
+ \ ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL,\
71
+ \ CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS\
72
+ \ AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\n\
73
+ 5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\
74
+ \ and in connection with the Llama Materials, neither Meta nor Licensee may use\
75
+ \ any name or mark owned by or associated with the other or any of its affiliates,\
76
+ \ except as required for reasonable and customary use in describing and redistributing\
77
+ \ the Llama Materials.\nb. Subject to Meta's ownership of Llama Materials and derivatives\
78
+ \ made by or for Meta, with respect to any derivative works and modifications of\
79
+ \ the Llama Materials that are made by you, as between you and Meta, you are and\
80
+ \ will be the owner of such derivative works and modifications.\nc. If you institute\
81
+ \ litigation or other proceedings against Meta or any entity (including a cross-claim\
82
+ \ or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 2 outputs\
83
+ \ or results, or any portion of any of the foregoing, constitutes infringement\
84
+ \ of intellectual property or other rights owned or licensable by you, then any\
85
+ \ licenses granted to you under this Agreement shall terminate as of the date such\
86
+ \ litigation or claim is filed or instituted. You will indemnify and hold harmless\
87
+ \ Meta from and against any claim by any third party arising out of or related \
88
+ \ to your use or distribution of the Llama Materials.\n6. Term and Termination.\
89
+ \ The term of this Agreement will commence upon your acceptance of this Agreement\
90
+ \ or access to the Llama Materials and will continue in full force and effect until\
91
+ \ terminated in accordance with the terms and conditions herein. Meta may terminate\
92
+ \ this Agreement if you are in breach of any term or condition of this Agreement.\
93
+ \ Upon termination of this Agreement, you shall delete and cease use of the Llama\
94
+ \ Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\
95
+ \ \n7. Governing Law and Jurisdiction. This Agreement will be governed and construed\
96
+ \ under the laws of the State of California without regard to choice of law principles,\
97
+ \ and the UN Convention on Contracts for the International Sale of Goods does not\
98
+ \ apply to this Agreement. The courts of California shall have exclusive jurisdiction\
99
+ \ of any dispute arising out of this Agreement. \n### Llama 2 Acceptable Use Policy\n\
100
+ Meta is committed to promoting safe and fair use of its tools and features, including\
101
+ \ Llama 2. If you access or use Llama 2, you agree to this Acceptable Use Policy\
102
+ \ (“Policy”). The most recent copy of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy).\n\
103
+ #### Prohibited Uses\nWe want everyone to use Llama 2 safely and responsibly. You\
104
+ \ agree you will not use, or allow others to use, Llama 2 to:\n1. Violate the law\
105
+ \ or others’ rights, including to:\n 1. Engage in, promote, generate, contribute\
106
+ \ to, encourage, plan, incite, or further illegal or unlawful activity or content,\
107
+ \ such as: \n 1. Violence or terrorism \n 2. Exploitation or harm\
108
+ \ to children, including the solicitation, creation, acquisition, or dissemination\
109
+ \ of child exploitative content or failure to report Child Sexual Abuse Material\n\
110
+ \ 3. Human trafficking, exploitation, and sexual violence\n 4.\
111
+ \ The illegal distribution of information or materials to minors, including obscene\
112
+ \ materials, or failure to employ legally required age-gating in connection with\
113
+ \ such information or materials.\n 5. Sexual solicitation\n 6.\
114
+ \ Any other criminal activity\n 2. Engage in, promote, incite, or facilitate\
115
+ \ the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
116
+ \ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\
117
+ \ or harmful conduct in the provision of employment, employment benefits, credit,\
118
+ \ housing, other economic benefits, or other essential goods and services\n \
119
+ \ 4. Engage in the unauthorized or unlicensed practice of any profession including,\
120
+ \ but not limited to, financial, legal, medical/health, or related professional\
121
+ \ practices \n 5. Collect, process, disclose, generate, or infer health, demographic,\
122
+ \ or other sensitive personal or private information about individuals without rights\
123
+ \ and consents required by applicable laws\n 6. Engage in or facilitate any\
124
+ \ action or generate any content that infringes, misappropriates, or otherwise violates\
125
+ \ any third-party rights, including the outputs or results of any products or services\
126
+ \ using the Llama 2 Materials\n 7. Create, generate, or facilitate the creation\
127
+ \ of malicious code, malware, computer viruses or do anything else that could disable,\
128
+ \ overburden, interfere with or impair the proper working, integrity, operation\
129
+ \ or appearance of a website or computer system \n2. Engage in, promote, incite,\
130
+ \ facilitate, or assist in the planning or development of activities that present\
131
+ \ a risk of death or bodily harm to individuals, including use of Llama 2 related\
132
+ \ to the following:\n 1. Military, warfare, nuclear industries or applications,\
133
+ \ espionage, use for materials or activities that are subject to the International\
134
+ \ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
135
+ \ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
136
+ \ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
137
+ \ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
138
+ \ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
139
+ \ content intended to incite or promote violence, abuse, or any infliction of bodily\
140
+ \ harm to an individual\n3. Intentionally deceive or mislead others, including use\
141
+ \ of Llama 2 related to the following:\n 1. Generating, promoting, or furthering\
142
+ \ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
143
+ \ or furthering defamatory content, including the creation of defamatory statements,\
144
+ \ images, or other content\n 3. Generating, promoting, or further distributing\
145
+ \ spam\n 4. Impersonating another individual without consent, authorization,\
146
+ \ or legal right\n 5. Representing that the use of Llama 2 or outputs are human-generated\n\
147
+ \ 6. Generating or facilitating false online engagement, including fake reviews\
148
+ \ and other means of fake online engagement \n 4. Fail to appropriately disclose\
149
+ \ to end users any known dangers of your AI system \nPlease report any violation\
150
+ \ of this Policy, software “bug,” or other problems that could lead to a violation\
151
+ \ of this Policy through one of the following means: \n * Reporting issues with\
152
+ \ the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)\n\
153
+ \ * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\n\
154
+ \ * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\
155
+ \ \n * Reporting violations of the Acceptable Use Policy or unlicensed uses of\
156
+ \ Llama: [[email protected]](mailto:[email protected])"
157
+ extra_gated_fields:
158
+ First Name: text
159
+ Last Name: text
160
+ Date of birth: date_picker
161
+ Country: country
162
+ Affiliation: text
163
+ geo: ip_location
164
+ ? By clicking Submit below I accept the terms of the license and acknowledge that
165
+ the information I provide will be collected stored processed and shared in accordance
166
+ with the Meta Privacy Policy
167
+ : checkbox
168
+ extra_gated_description: The information you provide will be collected, stored, processed
169
+ and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
170
+ extra_gated_button_content: Submit
171
+ pipeline_tag: text-generation
172
+ ---
173
+
174
+ # zhentaoyu/Llama-2-7b-chat-hf-Q4_0-GGUF
175
+ This model was converted to GGUF format from [`meta-llama/Llama-2-7b-chat-hf`](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
176
+ Refer to the [original model card](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) for more details on the model.
177
+
178
+ ## Use with llama.cpp
179
+ Install llama.cpp through brew (works on Mac and Linux)
180
+
181
+ ```bash
182
+ brew install llama.cpp
183
+
184
+ ```
185
+ Invoke the llama.cpp server or the CLI.
186
+
187
+ ### CLI:
188
+ ```bash
189
+ llama --hf-repo zhentaoyu/Llama-2-7b-chat-hf-Q4_0-GGUF --hf-file llama-2-7b-chat-hf-q4_0.gguf -p "The meaning to life and the universe is"
190
+ ```
191
+
192
+ ### Server:
193
+ ```bash
194
+ llama-server --hf-repo zhentaoyu/Llama-2-7b-chat-hf-Q4_0-GGUF --hf-file llama-2-7b-chat-hf-q4_0.gguf -c 2048
195
+ ```
196
+
197
+ 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.
198
+
199
+ Step 1: Clone llama.cpp from GitHub.
200
+ ```
201
+ git clone https://github.com/ggerganov/llama.cpp
202
+ ```
203
+
204
+ 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).
205
+ ```
206
+ cd llama.cpp && LLAMA_CURL=1 make
207
+ ```
208
+
209
+ Step 3: Run inference through the main binary.
210
+ ```
211
+ ./main --hf-repo zhentaoyu/Llama-2-7b-chat-hf-Q4_0-GGUF --hf-file llama-2-7b-chat-hf-q4_0.gguf -p "The meaning to life and the universe is"
212
+ ```
213
+ or
214
+ ```
215
+ ./server --hf-repo zhentaoyu/Llama-2-7b-chat-hf-Q4_0-GGUF --hf-file llama-2-7b-chat-hf-q4_0.gguf -c 2048
216
+ ```