mradermacher commited on
Commit
80fc1a1
1 Parent(s): ef5c8fd

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +245 -0
README.md CHANGED
@@ -1,6 +1,251 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: -->
6
  static quants of https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.3-70B-Instruct
3
+ extra_gated_button_content: Submit
4
+ extra_gated_fields:
5
+ Affiliation: text
6
+ ? By clicking Submit below I accept the terms of the license and acknowledge that
7
+ the information I provide will be collected stored processed and shared in accordance
8
+ with the Meta Privacy Policy
9
+ : checkbox
10
+ Country: country
11
+ Date of birth: date_picker
12
+ First Name: text
13
+ Job title:
14
+ options:
15
+ - Student
16
+ - Research Graduate
17
+ - AI researcher
18
+ - AI developer/engineer
19
+ - Reporter
20
+ - Other
21
+ type: select
22
+ Last Name: text
23
+ geo: ip_location
24
+ extra_gated_prompt: "### LLAMA 3.3 COMMUNITY LICENSE AGREEMENT\nLlama 3.3 Version
25
+ Release Date: December 6, 2024\n\"Agreement\" means the terms and conditions for
26
+ use, reproduction, distribution and modification of the Llama Materials set forth
27
+ herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying
28
+ Llama 3.3 distributed by Meta at [https://www.llama.com/docs/overview](https://llama.com/docs/overview).\n\"Licensee\"
29
+ or \"you\" means you, or your employer or any other person or entity (if you are
30
+ entering into this Agreement on such person or entity’s behalf), of the age required
31
+ under applicable laws, rules or regulations to provide legal consent and that has
32
+ legal authority to bind your employer or such other person or entity if you are
33
+ entering in this Agreement on their behalf.\n\"Llama 3.3\" means the foundational
34
+ large language models and software and algorithms, including machine-learning model
35
+ code, trained model weights, inference-enabling code, training-enabling code, fine-tuning
36
+ enabling code and other elements of the foregoing distributed by Meta at [https://www.llama.com/llama-downloads](https://www.llama.com/llama-downloads).\n\"Llama
37
+ Materials\" means, collectively, Meta’s proprietary Llama 3.3 and Documentation
38
+ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\"
39
+ means Meta Platforms Ireland Limited (if you are located in or, if you are an entity,
40
+ your principal place of business is in the EEA or Switzerland) and Meta Platforms,
41
+ Inc. (if you are located outside of the EEA or Switzerland).\nBy clicking “I Accept”
42
+ below or by using or distributing any portion or element of the Llama Materials,
43
+ you agree to be bound by this Agreement.\n1. License Rights and Redistribution.\na.
44
+ Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and
45
+ royalty-free limited license under Meta’s intellectual property or other rights
46
+ owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy,
47
+ create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution
48
+ and Use.\ni. If you distribute or make available the Llama Materials (or any derivative
49
+ works thereof), or a product or service (including another AI model) that contains
50
+ any of them, you shall (A) provide a copy of this Agreement with any such Llama
51
+ Materials; and (B) prominently display “Built with Llama” on a related website,
52
+ user interface, blogpost, about page, or product documentation. If you use the Llama
53
+ Materials or any outputs or results of the Llama Materials to create, train, fine
54
+ tune, or otherwise improve an AI model, which is distributed or made available,
55
+ you shall also include “Llama” at the beginning of any such AI model name.\nii.
56
+ If you receive Llama Materials, or any derivative works thereof, from a Licensee
57
+ as part of an integrated end user product, then Section 2 of this Agreement will
58
+ not apply to you. \niii. You must retain in all copies of the Llama Materials that
59
+ you distribute the following attribution notice within a “Notice” text file distributed
60
+ as a part of such copies: “Llama 3.3 is licensed under the Llama 3.3 Community License,
61
+ Copyright © Meta Platforms, Inc. All Rights Reserved.”\niv. Your use of the Llama
62
+ Materials must comply with applicable laws and regulations (including trade compliance
63
+ laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials
64
+ (available at [https://www.llama.com/llama3\\_3/use-policy](https://www.llama.com/llama3_3/use-policy)),
65
+ which is hereby incorporated by reference into this Agreement. \n2. Additional
66
+ Commercial Terms. If, on the Llama 3.3 version release date, the monthly active
67
+ users of the products or services made available by or for Licensee, or Licensee’s
68
+ affiliates, is greater than 700 million monthly active users in the preceding calendar
69
+ month, you must request a license from Meta, which Meta may grant to you in its
70
+ sole discretion, and you are not authorized to exercise any of the rights under
71
+ this Agreement unless or until Meta otherwise expressly grants you such rights.\n3.
72
+ Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND
73
+ ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES
74
+ OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,
75
+ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,
76
+ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING
77
+ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY
78
+ RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4.
79
+ Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER
80
+ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,
81
+ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,
82
+ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META
83
+ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5.
84
+ Intellectual Property.\na. No trademark licenses are granted under this Agreement,
85
+ and in connection with the Llama Materials, neither Meta nor Licensee may use any
86
+ name or mark owned by or associated with the other or any of its affiliates, except
87
+ as required for reasonable and customary use in describing and redistributing the
88
+ Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license
89
+ to use “Llama” (the “Mark”) solely as required to comply with the last sentence
90
+ of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible
91
+ at [https://about.meta.com/brand/resources/meta/company-brand/](https://about.meta.com/brand/resources/meta/company-brand/)[)](https://en.facebookbrand.com/).
92
+ All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb.
93
+ Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta,
94
+ with respect to any derivative works and modifications of the Llama Materials that
95
+ are made by you, as between you and Meta, you are and will be the owner of such
96
+ derivative works and modifications.\nc. If you institute litigation or other proceedings
97
+ against Meta or any entity (including a cross-claim or counterclaim in a lawsuit)
98
+ alleging that the Llama Materials or Llama 3.3 outputs or results, or any portion
99
+ of any of the foregoing, constitutes infringement of intellectual property or other
100
+ rights owned or licensable by you, then any licenses granted to you under this Agreement
101
+ shall terminate as of the date such litigation or claim is filed or instituted.
102
+ You will indemnify and hold harmless Meta from and against any claim by any third
103
+ party arising out of or related to your use or distribution of the Llama Materials.\n6.
104
+ Term and Termination. The term of this Agreement will commence upon your acceptance
105
+ of this Agreement or access to the Llama Materials and will continue in full force
106
+ and effect until terminated in accordance with the terms and conditions herein.
107
+ Meta may terminate this Agreement if you are in breach of any term or condition
108
+ of this Agreement. Upon termination of this Agreement, you shall delete and cease
109
+ use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of
110
+ this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed
111
+ and construed under the laws of the State of California without regard to choice
112
+ of law principles, and the UN Convention on Contracts for the International Sale
113
+ of Goods does not apply to this Agreement. The courts of California shall have exclusive
114
+ jurisdiction of any dispute arising out of this Agreement.\n### Llama 3.3 Acceptable
115
+ Use Policy\nMeta is committed to promoting safe and fair use of its tools and features,
116
+ including Llama 3.3. If you access or use Llama 3.3, you agree to this Acceptable
117
+ Use Policy (“**Policy**”). The most recent copy of this policy can be found at [https://www.llama.com/llama3\\_3/use-policy](https://www.llama.com/llama3_3/use-policy).\nProhibited
118
+ Uses\nWe want everyone to use Llama 3.3 safely and responsibly. You agree you will
119
+ not use, or allow others to use, Llama 3.3 to:\n1. Violate the law or others’ rights,
120
+ including to:\n\n 1. Engage in, promote, generate, contribute to, encourage, plan,
121
+ incite, or further illegal or unlawful activity or content, such as: \n 1.
122
+ Violence or terrorism \n 2. Exploitation or harm to children, including the
123
+ solicitation, creation, acquisition, or dissemination of child exploitative content
124
+ or failure to report Child Sexual Abuse Material \n 3. Human trafficking,
125
+ exploitation, and sexual violence \n 4. The illegal distribution of information
126
+ or materials to minors, including obscene materials, or failure to employ legally
127
+ required age-gating in connection with such information or materials. \n 5.
128
+ Sexual solicitation \n 6. Any other criminal activity\n\n 2. Engage in,
129
+ promote, incite, or facilitate the harassment, abuse, threatening, or bullying of
130
+ individuals or groups of individuals\n\n 3. Engage in, promote, incite, or facilitate
131
+ discrimination or other unlawful or harmful conduct in the provision of employment,
132
+ employment benefits, credit, housing, other economic benefits, or other essential
133
+ goods and services\n\n 4. Engage in the unauthorized or unlicensed practice of
134
+ any profession including, but not limited to, financial, legal, medical/health,
135
+ or related professional practices\n\n 5. Collect, process, disclose, generate,
136
+ or infer private or sensitive information about individuals, including information
137
+ about individuals’ identity, health, or demographic information, unless you have
138
+ obtained the right to do so in accordance with applicable law\n\n 6. Engage in
139
+ or facilitate any action or generate any content that infringes, misappropriates,
140
+ or otherwise violates any third-party rights, including the outputs or results of
141
+ any products or services using the Llama Materials\n\n 7. Create, generate, or
142
+ facilitate the creation of malicious code, malware, computer viruses or do anything
143
+ else that could disable, overburden, interfere with or impair the proper working,
144
+ integrity, operation or appearance of a website or computer system\n\n 8. Engage
145
+ in any action, or facilitate any action, to intentionally circumvent or remove usage
146
+ restrictions or other safety measures, or to enable functionality disabled by Meta\n\n2.
147
+ Engage in, promote, incite, facilitate, or assist in the planning or development
148
+ of activities that present a risk of death or bodily harm to individuals, including
149
+ use of Llama 3.3 related to the following:\n\n 1. Military, warfare, nuclear industries
150
+ or applications, espionage, use for materials or activities that are subject to
151
+ the International Traffic Arms Regulations (ITAR) maintained by the United States
152
+ Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989
153
+ or the Chemical Weapons Convention Implementation Act of 1997\n\n 2. Guns and
154
+ illegal weapons (including weapon development)\n\n 3. Illegal drugs and regulated/controlled
155
+ substances\n\n 4. Operation of critical infrastructure, transportation technologies,
156
+ or heavy machinery\n\n 5. Self-harm or harm to others, including suicide, cutting,
157
+ and eating disorders\n\n 6. Any content intended to incite or promote violence,
158
+ abuse, or any infliction of bodily harm to an individual\n\n3. Intentionally deceive
159
+ or mislead others, including use of Llama 3.3 related to the following:\n\n 1.
160
+ Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\n
161
+ \ 2. Generating, promoting, or furthering defamatory content, including the creation
162
+ of defamatory statements, images, or other content\n\n 3. Generating, promoting,
163
+ or further distributing spam\n\n 4. Impersonating another individual without consent,
164
+ authorization, or legal right\n\n 5. Representing that the use of Llama 3.3 or
165
+ outputs are human-generated\n\n 6. Generating or facilitating false online engagement,
166
+ including fake reviews and other means of fake online engagement\n\n4. Fail to appropriately
167
+ disclose to end users any known dangers of your AI system\n5. Interact with third
168
+ party tools, models, or software designed to generate unlawful content or engage
169
+ in unlawful or harmful conduct and/or represent that the outputs of such tools,
170
+ models, or software are associated with Meta or Llama 3.3\nWith respect to any multimodal
171
+ models included in Llama 3.3, the rights granted under Section 1(a) of the Llama
172
+ 3.3 Community License Agreement are not being granted to you if you are an individual
173
+ domiciled in, or a company with a principal place of business in, the European Union.
174
+ This restriction does not apply to end users of a product or service that incorporates
175
+ any such multimodal models.\nPlease report any violation of this Policy, software
176
+ “bug,” or other problems that could lead to a violation of this Policy through one
177
+ of the following means:\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)
178
+ \ * Reporting risky content generated by the model: [developers.facebook.com/llama\\_output\\_feedback](http://developers.facebook.com/llama_output_feedback)
179
+ \ * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
180
+ \ * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
181
+ 3.3: LlamaUseReport@meta.com "
182
+ language:
183
+ - en
184
+ - fr
185
+ - it
186
+ - pt
187
+ - hi
188
+ - es
189
+ - th
190
+ - de
191
+ library_name: transformers
192
+ license: llama3.3
193
+ quantized_by: mradermacher
194
+ tags:
195
+ - facebook
196
+ - meta
197
+ - pytorch
198
+ - llama
199
+ - llama-3
200
+ ---
201
+ ## About
202
+
203
  <!-- ### quantize_version: 2 -->
204
  <!-- ### output_tensor_quantised: 1 -->
205
  <!-- ### convert_type: hf -->
206
  <!-- ### vocab_type: -->
207
  <!-- ### tags: -->
208
  static quants of https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
209
+
210
+ <!-- provided-files -->
211
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.3-70B-Instruct-i1-GGUF
212
+ ## Usage
213
+
214
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
215
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
216
+ more details, including on how to concatenate multi-part files.
217
+
218
+ ## Provided Quants
219
+
220
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
221
+
222
+ | Link | Type | Size/GB | Notes |
223
+ |:-----|:-----|--------:|:------|
224
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-Instruct-GGUF/resolve/main/Llama-3.3-70B-Instruct.Q2_K.gguf) | Q2_K | 26.5 | |
225
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-Instruct-GGUF/resolve/main/Llama-3.3-70B-Instruct.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
226
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-Instruct-GGUF/resolve/main/Llama-3.3-70B-Instruct.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
227
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-Instruct-GGUF/resolve/main/Llama-3.3-70B-Instruct.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
228
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.3-70B-Instruct-GGUF/resolve/main/Llama-3.3-70B-Instruct.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
229
+ | [PART 1](https://huggingface.co/mradermacher/Llama-3.3-70B-Instruct-GGUF/resolve/main/Llama-3.3-70B-Instruct.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3.3-70B-Instruct-GGUF/resolve/main/Llama-3.3-70B-Instruct.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
230
+ | [PART 1](https://huggingface.co/mradermacher/Llama-3.3-70B-Instruct-GGUF/resolve/main/Llama-3.3-70B-Instruct.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3.3-70B-Instruct-GGUF/resolve/main/Llama-3.3-70B-Instruct.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
231
+
232
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
233
+ types (lower is better):
234
+
235
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
236
+
237
+ And here are Artefact2's thoughts on the matter:
238
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
239
+
240
+ ## FAQ / Model Request
241
+
242
+ See https://huggingface.co/mradermacher/model_requests for some answers to
243
+ questions you might have and/or if you want some other model quantized.
244
+
245
+ ## Thanks
246
+
247
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
248
+ me use its servers and providing upgrades to my workstation to enable
249
+ this work in my free time.
250
+
251
+ <!-- end -->