royleibov commited on
Commit
e8b34da
1 Parent(s): 3f40640

Add ZipNN stuff

Browse files
Files changed (1) hide show
  1. README.md +133 -237
README.md CHANGED
@@ -17,241 +17,97 @@ tags:
17
  - llama
18
  - llama-3
19
  widget:
20
- - example_title: rococo art
21
- messages:
22
- - role: user
23
- content:
24
- - type: text
25
- text: Which era does this piece belong to? Give details about the era.
26
- - type: image_url
27
- image_url:
28
- url: https://huggingface.co/datasets/huggingface/release-assets/resolve/main/rococo.jpg
29
- - role: assistant
30
- content: |
31
- The piece is a painting of a woman in a red dress, surrounded by gold and white ornate details. The woman is depicted in mid-air, with her arms outstretched and her legs bent at the knees. She is holding a bouquet of flowers in her right hand and a fruit in her left hand.
32
-
33
- The background of the painting is a light blue sky with pink clouds, and there are also some pink flowers and green leaves surrounding the woman. The overall atmosphere of the painting is one of joy and celebration, as if the woman is dancing or celebrating something.
34
-
35
- This piece belongs to the Rococo era, which was a style of art and architecture that emerged in Europe in the 18th century. The Rococo style is characterized by its use of pastel colors, curved lines, and ornate details. It was popularized during the reign of King Louis XV of France, who ruled from 1715 to 1774.
36
- - example_title: diagram understanding
37
- messages:
38
- - role: user
39
- content:
40
- - type: text
41
- text: Where do the droughts happen according to this diagram?
42
- - type: image_url
43
- image_url:
44
- url: https://huggingface.co/datasets/huggingface/release-assets/resolve/main/weather_events.png
45
- - role: assistant
46
- content: |
47
- # Drought Regions in 2016
48
-
49
- According to the diagram, the regions that experienced severe droughts in 2016 are:
50
-
51
- - **Eastern and Southern Africa**: This region was severely affected by droughts, with significant impacts on agriculture and water resources.
52
- - **Western and Southern Africa**: Droughts also occurred in this region, leading to food insecurity and other challenges.
53
-
54
- These regions were particularly vulnerable to droughts in 2016, highlighting the need for effective water management strategies and climate resilience measures.
55
- - example_title: document qa
56
- messages:
57
- - role: user
58
- content:
59
- - type: text
60
- text: How long does it take from invoice date to due date? Be short and concise.
61
- - type: image_url
62
- image_url:
63
- url: https://huggingface.co/datasets/huggingface/release-assets/resolve/main/invoice.png
64
- - role: assistant
65
- content: |
66
- To determine the time gap between the invoice date and the due date, we need to calculate the difference between these two dates.
67
-
68
- Invoice Date: February 11, 2019
69
- Due Date: February 26, 2019
70
-
71
- Step 1: Calculate the Difference in Days
72
-
73
- February 26 - February 11 = 15 days
74
-
75
- Therefore, the time gap between the invoice date and the due date is 15 days.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  license: llama3.2
77
- extra_gated_prompt: >-
78
- ### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT
79
-
80
-
81
- Llama 3.2 Version Release Date: September 25, 2024
82
-
83
-
84
- “Agreement” means the terms and conditions for use, reproduction, distribution
85
- and modification of the Llama Materials set forth herein.
86
-
87
-
88
- “Documentation” means the specifications, manuals and documentation accompanying Llama 3.2
89
- distributed by Meta at https://llama.meta.com/doc/overview.
90
-
91
-
92
- “Licensee” or “you” means you, or your employer or any other person or entity (if you are
93
- entering into this Agreement on such person or entity’s behalf), of the age required under
94
- applicable laws, rules or regulations to provide legal consent and that has legal authority
95
- to bind your employer or such other person or entity if you are entering in this Agreement
96
- on their behalf.
97
-
98
-
99
- “Llama 3.2” means the foundational large language models and software and algorithms, including
100
- machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
101
- fine-tuning enabling code and other elements of the foregoing distributed by Meta at
102
- https://www.llama.com/llama-downloads.
103
-
104
-
105
- “Llama Materials” means, collectively, Meta’s proprietary Llama 3.2 and Documentation (and
106
- any portion thereof) made available under this Agreement.
107
-
108
-
109
- “Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or,
110
- if you are an entity, your principal place of business is in the EEA or Switzerland)
111
- and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
112
-
113
-
114
- By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials,
115
- you agree to be bound by this Agreement.
116
-
117
-
118
- 1. License Rights and Redistribution.
119
-
120
- a. Grant of Rights. You are granted a non-exclusive, worldwide,
121
- non-transferable and royalty-free limited license under Meta’s intellectual property or other rights
122
- owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works
123
- of, and make modifications to the Llama Materials.
124
-
125
- b. Redistribution and Use.
126
-
127
- i. If you distribute or make available the Llama Materials (or any derivative works thereof),
128
- or a product or service (including another AI model) that contains any of them, you shall (A) provide
129
- a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama”
130
- on a related website, user interface, blogpost, about page, or product documentation. If you use the
131
- Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or
132
- otherwise improve an AI model, which is distributed or made available, you shall also include “Llama”
133
- at the beginning of any such AI model name.
134
-
135
- ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
136
- of an integrated end user product, then Section 2 of this Agreement will not apply to you.
137
-
138
- iii. You must retain in all copies of the Llama Materials that you distribute the
139
- following attribution notice within a “Notice” text file distributed as a part of such copies:
140
- “Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,
141
- Inc. All Rights Reserved.”
142
-
143
- iv. Your use of the Llama Materials must comply with applicable laws and regulations
144
- (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for
145
- the Llama Materials (available at https://www.llama.com/llama3_2/use-policy), which is hereby
146
- incorporated by reference into this Agreement.
147
-
148
- 2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users
149
- of the products or services made available by or for Licensee, or Licensee’s affiliates,
150
- is greater than 700 million monthly active users in the preceding calendar month, you must request
151
- a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to
152
- exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
153
-
154
- 3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND
155
- RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS
156
- ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES
157
- OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
158
- FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED
159
- WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
160
-
161
- 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,
162
- WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
163
- FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN
164
- IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
165
-
166
- 5. Intellectual Property.
167
-
168
- a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials,
169
- neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates,
170
- except as required for reasonable and customary use in describing and redistributing the Llama Materials or as
171
- set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required
172
- to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible
173
- at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark
174
- will inure to the benefit of Meta.
175
-
176
- b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any
177
- derivative works and modifications of the Llama Materials that are made by you, as between you and Meta,
178
- you are and will be the owner of such derivative works and modifications.
179
-
180
- c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or
181
- counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion
182
- of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable
183
- by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or
184
- claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third
185
- party arising out of or related to your use or distribution of the Llama Materials.
186
-
187
- 6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access
188
- to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms
189
- and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this
190
- Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3,
191
- 4 and 7 shall survive the termination of this Agreement.
192
-
193
- 7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of
194
- California without regard to choice of law principles, and the UN Convention on Contracts for the International
195
- Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of
196
- any dispute arising out of this Agreement.
197
-
198
- ### Llama 3.2 Acceptable Use Policy
199
-
200
- Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.2.
201
- If you access or use Llama 3.2, you agree to this Acceptable Use Policy (“**Policy**”).
202
- The most recent copy of this policy can be found at
203
- [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).
204
-
205
- #### Prohibited Uses
206
-
207
- We want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to:
208
-
209
- 1. Violate the law or others’ rights, including to:
210
- 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
211
- 1. Violence or terrorism
212
- 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
213
- 3. Human trafficking, exploitation, and sexual violence
214
- 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
215
- 5. Sexual solicitation
216
- 6. Any other criminal activity
217
- 1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
218
- 2. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
219
- 3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
220
- 4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
221
- 5. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
222
- 6. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
223
- 7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta 
224
- 2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following:
225
- 8. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
226
- 9. Guns and illegal weapons (including weapon development)
227
- 10. Illegal drugs and regulated/controlled substances
228
- 11. Operation of critical infrastructure, transportation technologies, or heavy machinery
229
- 12. Self-harm or harm to others, including suicide, cutting, and eating disorders
230
- 13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
231
- 3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following:
232
- 14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
233
- 15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
234
- 16. Generating, promoting, or further distributing spam
235
- 17. Impersonating another individual without consent, authorization, or legal right
236
- 18. Representing that the use of Llama 3.2 or outputs are human-generated
237
- 19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 
238
- 4. Fail to appropriately disclose to end users any known dangers of your AI system
239
- 5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2
240
-
241
-
242
- With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
243
-
244
-
245
- Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
246
-
247
-
248
- * Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)
249
-
250
- * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
251
-
252
- * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
253
-
254
- * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: LlamaUseReport@meta.com
255
  extra_gated_fields:
256
  First Name: text
257
  Last Name: text
@@ -275,7 +131,44 @@ extra_gated_description: >-
275
  Policy](https://www.facebook.com/privacy/policy/).
276
  extra_gated_button_content: Submit
277
  extra_gated_eu_disallowed: true
 
 
278
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
 
280
  ## Model Information
281
 
@@ -334,8 +227,11 @@ import requests
334
  import torch
335
  from PIL import Image
336
  from transformers import MllamaForConditionalGeneration, AutoProcessor
 
 
 
337
 
338
- model_id = "meta-llama/Llama-3.2-11B-Vision-Instruct"
339
 
340
  model = MllamaForConditionalGeneration.from_pretrained(
341
  model_id,
@@ -367,7 +263,7 @@ Please, follow the instructions in the [repository](https://github.com/meta-llam
367
  To download the original checkpoints, you can use `huggingface-cli` as follows:
368
 
369
  ```
370
- huggingface-cli download meta-llama/Llama-3.2-11B-Vision-Instruct --include "original/*" --local-dir Llama-3.2-11B-Vision-Instruct
371
  ```
372
 
373
  ## Hardware and Software
@@ -487,4 +383,4 @@ Our attack automation study focused on evaluating the capabilities of LLMs when
487
 
488
  **Values:** The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
489
 
490
- **Testing:** But Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.
 
17
  - llama
18
  - llama-3
19
  widget:
20
+ - example_title: rococo art
21
+ messages:
22
+ - role: user
23
+ content:
24
+ - type: text
25
+ text: Which era does this piece belong to? Give details about the era.
26
+ - type: image_url
27
+ image_url:
28
+ url: >-
29
+ https://huggingface.co/datasets/huggingface/release-assets/resolve/main/rococo.jpg
30
+ - role: assistant
31
+ content: >
32
+ The piece is a painting of a woman in a red dress, surrounded by gold and
33
+ white ornate details. The woman is depicted in mid-air, with her arms
34
+ outstretched and her legs bent at the knees. She is holding a bouquet of
35
+ flowers in her right hand and a fruit in her left hand.
36
+
37
+
38
+ The background of the painting is a light blue sky with pink clouds, and
39
+ there are also some pink flowers and green leaves surrounding the woman.
40
+ The overall atmosphere of the painting is one of joy and celebration, as
41
+ if the woman is dancing or celebrating something.
42
+
43
+
44
+ This piece belongs to the Rococo era, which was a style of art and
45
+ architecture that emerged in Europe in the 18th century. The Rococo style
46
+ is characterized by its use of pastel colors, curved lines, and ornate
47
+ details. It was popularized during the reign of King Louis XV of France,
48
+ who ruled from 1715 to 1774.
49
+ - example_title: diagram understanding
50
+ messages:
51
+ - role: user
52
+ content:
53
+ - type: text
54
+ text: Where do the droughts happen according to this diagram?
55
+ - type: image_url
56
+ image_url:
57
+ url: >-
58
+ https://huggingface.co/datasets/huggingface/release-assets/resolve/main/weather_events.png
59
+ - role: assistant
60
+ content: >
61
+ # Drought Regions in 2016
62
+
63
+
64
+ According to the diagram, the regions that experienced severe droughts in
65
+ 2016 are:
66
+
67
+
68
+ - **Eastern and Southern Africa**: This region was severely affected by
69
+ droughts, with significant impacts on agriculture and water resources.
70
+
71
+ - **Western and Southern Africa**: Droughts also occurred in this region,
72
+ leading to food insecurity and other challenges.
73
+
74
+
75
+ These regions were particularly vulnerable to droughts in 2016,
76
+ highlighting the need for effective water management strategies and
77
+ climate resilience measures.
78
+ - example_title: document qa
79
+ messages:
80
+ - role: user
81
+ content:
82
+ - type: text
83
+ text: >-
84
+ How long does it take from invoice date to due date? Be short and
85
+ concise.
86
+ - type: image_url
87
+ image_url:
88
+ url: >-
89
+ https://huggingface.co/datasets/huggingface/release-assets/resolve/main/invoice.png
90
+ - role: assistant
91
+ content: >
92
+ To determine the time gap between the invoice date and the due date, we
93
+ need to calculate the difference between these two dates.
94
+
95
+
96
+ Invoice Date: February 11, 2019
97
+
98
+ Due Date: February 26, 2019
99
+
100
+
101
+ Step 1: Calculate the Difference in Days
102
+
103
+
104
+ February 26 - February 11 = 15 days
105
+
106
+
107
+ Therefore, the time gap between the invoice date and the due date is 15
108
+ days.
109
  license: llama3.2
110
+ extra_gated_prompt: "### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\n\nLlama 3.2 Version Release Date: September 25, 2024\n\n“Agreement” means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\n“Documentation” means the specifications, manuals and documentation accompanying Llama 3.2 distributed by Meta at https://llama.meta.com/doc/overview.\n\n“Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\n“Llama 3.2” means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://www.llama.com/llama-downloads.\n\n“Llama Materials” means, collectively, Meta’s proprietary Llama 3.2 and Documentation (and any portion thereof) made available under this Agreement.\n\n“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). \n\nBy clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.\n\n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials. \nb. Redistribution and Use. \ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you. \niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://www.llama.com/llama3_2/use-policy), which is hereby incorporated by reference into this Agreement.\n \n2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement. \n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement. \n### Llama 3.2 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy (“**Policy**”). The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\n#### Prohibited Uses\nWe want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to:\n1. Violate the law or others’ rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 2. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law\n 5. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 6. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n 7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta\_\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following:\n 8. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997\n 9. Guns and illegal weapons (including weapon development)\n 10. Illegal drugs and regulated/controlled substances\n 11. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 12. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following:\n 14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 16. Generating, promoting, or further distributing spam\n 17. Impersonating another individual without consent, authorization, or legal right\n 18. Representing that the use of Llama 3.2 or outputs are human-generated\n 19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\_\n4. Fail to appropriately disclose to end users any known dangers of your AI system 5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2\n\nWith respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.\n\nPlease report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:\n\n* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\n* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\n* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\n* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: LlamaUseReport@meta.com"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
111
  extra_gated_fields:
112
  First Name: text
113
  Last Name: text
 
131
  Policy](https://www.facebook.com/privacy/policy/).
132
  extra_gated_button_content: Submit
133
  extra_gated_eu_disallowed: true
134
+ base_model:
135
+ - meta-llama/Llama-3.2-11B-Vision-Instruct
136
  ---
137
+ # Disclaimer and Requirements
138
+
139
+ This model is a clone of [**meta-llama/Llama-3.2-11B-Vision-Instruct**](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct) compressed using ZipNN. Compressed losslessly to 67% its original size, ZipNN saved ~3GB in storage and potentially ~4.5TB in data transfer **monthly**.
140
+
141
+ ### Requirement
142
+
143
+ In order to use the model, ZipNN is necessary:
144
+ ```bash
145
+ pip install zipnn
146
+ ```
147
+ ### Use This Model
148
+ ```python
149
+ # Load model directly
150
+ from transformers import AutoProcessor, AutoModelForPreTraining
151
+ from zipnn import zipnn_hf
152
+
153
+ zipnn_hf()
154
+
155
+ processor = AutoProcessor.from_pretrained("royleibov/Llama-3.2-11B-Vision-Instruct-ZipNN-Compressed")
156
+ model = AutoModelForPreTraining.from_pretrained("royleibov/Llama-3.2-11B-Vision-Instruct-ZipNN-Compressed")
157
+ ```
158
+ ### ZipNN
159
+ ZipNN also allows you to seemlessly save local disk space in your cache after the model is downloaded.
160
+
161
+ To compress the cached model, simply run:
162
+ ```bash
163
+ python zipnn_compress_path.py safetensors --model royleibov/Llama-3.2-11B-Vision-Instruct-ZipNN-Compressed --hf_cache
164
+ ```
165
+
166
+ The model will be decompressed automatically and safely as long as `zipnn_hf()` is added at the top of the file like in the [example above](#use-this-model).
167
+
168
+ To decompress manualy, simply run:
169
+ ```bash
170
+ python zipnn_decompress_path.py --model royleibov/Llama-3.2-11B-Vision-Instruct-ZipNN-Compressed --hf_cache
171
+ ```
172
 
173
  ## Model Information
174
 
 
227
  import torch
228
  from PIL import Image
229
  from transformers import MllamaForConditionalGeneration, AutoProcessor
230
+ from zipnn import zipnn_hf
231
+
232
+ zipnn_hf()
233
 
234
+ model_id = "royleibov/Llama-3.2-11B-Vision-Instruct-ZipNN-Compressed"
235
 
236
  model = MllamaForConditionalGeneration.from_pretrained(
237
  model_id,
 
263
  To download the original checkpoints, you can use `huggingface-cli` as follows:
264
 
265
  ```
266
+ huggingface-cli download royleibov/Llama-3.2-11B-Vision-Instruct-ZipNN-Compressed --include "original/*" --local-dir Llama-3.2-11B-Vision-Instruct-ZipNN-Compressed
267
  ```
268
 
269
  ## Hardware and Software
 
383
 
384
  **Values:** The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
385
 
386
+ **Testing:** But Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.