morriszms commited on
Commit
e88b09b
1 Parent(s): a0381eb

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Meta-Llama-3-70B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Meta-Llama-3-70B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Meta-Llama-3-70B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Meta-Llama-3-70B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Meta-Llama-3-70B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Meta-Llama-3-70B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Meta-Llama-3-70B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Meta-Llama-3-70B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Meta-Llama-3-70B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Meta-Llama-3-70B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Meta-Llama-3-70B-Instruct-Q6_K/Meta-Llama-3-70B-Instruct-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Meta-Llama-3-70B-Instruct-Q6_K/Meta-Llama-3-70B-Instruct-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Meta-Llama-3-70B-Instruct-Q8_0/Meta-Llama-3-70B-Instruct-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Meta-Llama-3-70B-Instruct-Q8_0/Meta-Llama-3-70B-Instruct-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Meta-Llama-3-70B-Instruct-Q8_0/Meta-Llama-3-70B-Instruct-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
Meta-Llama-3-70B-Instruct-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e9485c3c0c6ab096a04e01016c37b2dd6b3f6c3e58fc322430fc71e8fd9f626
3
+ size 26375108576
Meta-Llama-3-70B-Instruct-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df5ebd8f8e8f6fcff434ed136fd135b7c18edb1324be2425b6ab41216f981a62
3
+ size 37140592608
Meta-Llama-3-70B-Instruct-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:771bc8f68616b213cedb06f855461db7bbcfa38a147925dc6d4ef26501b1224a
3
+ size 34267494368
Meta-Llama-3-70B-Instruct-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb74e4b5ad6afa1eaed0e80833c4b0be7c72fded8a5fa4798fbbec25908f8fac
3
+ size 30912051168
Meta-Llama-3-70B-Instruct-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccef63f79a3b3a7b947924d825cddbf46ae4c4cd0f7db68f80c7c850dea61d87
3
+ size 39969732576
Meta-Llama-3-70B-Instruct-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc1caf33329235f98d448b4a353e0f36d10c5de405311de5e5d5866ce7b9dbd4
3
+ size 42520393696
Meta-Llama-3-70B-Instruct-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc62c2ab67128cc4b7ed79e6813bf903dc3bfd461ba4d5bb0ff00bd4e7318db5
3
+ size 40347219936
Meta-Llama-3-70B-Instruct-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b1df38cea70f654e5fd93a07a2336f337ce35ad908f810c600c776aeb81df7
3
+ size 48657446880
Meta-Llama-3-70B-Instruct-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1019742920ade0078ffacb97b74de3624feb8b1e8ea1d2737653a1dc0ab756ca
3
+ size 49949816800
Meta-Llama-3-70B-Instruct-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a216f9f38d752f795fd9cab4f1863db924dca4071fbe017df0f2928542aeb1
3
+ size 48657446880
Meta-Llama-3-70B-Instruct-Q6_K/Meta-Llama-3-70B-Instruct-Q6_K-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c21d2b18a2ca6d75ce848f92a054408645e368bba2295579de8833b07e9f41e4
3
+ size 34847470592
Meta-Llama-3-70B-Instruct-Q6_K/Meta-Llama-3-70B-Instruct-Q6_K-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f2ab9e4b61d3300d5c08d854a71cbf7fb144dbe648cb997df92972a39d7bd3
3
+ size 23040672928
Meta-Llama-3-70B-Instruct-Q8_0/Meta-Llama-3-70B-Instruct-Q8_0-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42692455e31c52401182315852aacdb626028189857a8583aa2b5491e68adffb
3
+ size 34980011040
Meta-Llama-3-70B-Instruct-Q8_0/Meta-Llama-3-70B-Instruct-Q8_0-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc10e4f10a32fd96a4461c1b6d336f506c316e4e7e5c6013b861ad31c6a9a02
3
+ size 34949976384
Meta-Llama-3-70B-Instruct-Q8_0/Meta-Llama-3-70B-Instruct-Q8_0-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f683fbc6289956f164fe0bba001c5698991e3450ca7c0c8eacd7001e1ca2cdd
3
+ size 5045062560
README.md ADDED
@@ -0,0 +1,254 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - facebook
7
+ - meta
8
+ - pytorch
9
+ - llama
10
+ - llama-3
11
+ - TensorBlock
12
+ - GGUF
13
+ license: other
14
+ license_name: llama3
15
+ license_link: LICENSE
16
+ extra_gated_prompt: "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version\
17
+ \ Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for\
18
+ \ use, reproduction, distribution and modification of the Llama Materials set forth\
19
+ \ herein.\n\"Documentation\" means the specifications, manuals and documentation\
20
+ \ accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\
21
+ \"Licensee\" or \"you\" means you, or your employer or any other person or entity\
22
+ \ (if you are entering into this Agreement on such person or entity’s behalf), of\
23
+ \ the age required under applicable laws, rules or regulations to provide legal\
24
+ \ consent and that has legal authority to bind your employer or such other person\
25
+ \ or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama\
26
+ \ 3\" means the foundational large language models and software and algorithms,\
27
+ \ including machine-learning model code, trained model weights, inference-enabling\
28
+ \ code, training-enabling code, fine-tuning enabling code and other elements of\
29
+ \ the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\
30
+ \"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation\
31
+ \ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"\
32
+ we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\
33
+ \ an entity, your principal place of business is in the EEA or Switzerland) and\
34
+ \ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n\
35
+ \ \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted\
36
+ \ a non-exclusive, worldwide, non-transferable and royalty-free limited license\
37
+ \ under Meta’s intellectual property or other rights owned by Meta embodied in the\
38
+ \ Llama Materials to use, reproduce, distribute, copy, create derivative works of,\
39
+ \ and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni.\
40
+ \ If you distribute or make available the Llama Materials (or any derivative works\
41
+ \ thereof), or a product or service that uses any of them, including another AI\
42
+ \ model, you shall (A) provide a copy of this Agreement with any such Llama Materials;\
43
+ \ and (B) prominently display “Built with Meta Llama 3” on a related website, user\
44
+ \ interface, blogpost, about page, or product documentation. If you use the Llama\
45
+ \ Materials to create, train, fine tune, or otherwise improve an AI model, which\
46
+ \ is distributed or made available, you shall also include “Llama 3” at the beginning\
47
+ \ of any such AI model name.\nii. If you receive Llama Materials, or any derivative\
48
+ \ works thereof, from a Licensee as part of an integrated end user product, then\
49
+ \ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\
50
+ \ copies of the Llama Materials that you distribute the following attribution notice\
51
+ \ within a “Notice” text file distributed as a part of such copies: “Meta Llama\
52
+ \ 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms,\
53
+ \ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
54
+ \ applicable laws and regulations (including trade compliance laws and regulations)\
55
+ \ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
56
+ \ https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference\
57
+ \ into this Agreement.\nv. You will not use the Llama Materials or any output or\
58
+ \ results of the Llama Materials to improve any other large language model (excluding\
59
+ \ Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If,\
60
+ \ on the Meta Llama 3 version release date, the monthly active users of the products\
61
+ \ or services made available by or for Licensee, or Licensee’s affiliates, is greater\
62
+ \ than 700 million monthly active users in the preceding calendar month, you must\
63
+ \ request a license from Meta, which Meta may grant to you in its sole discretion,\
64
+ \ and you are not authorized to exercise any of the rights under this Agreement\
65
+ \ unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer\
66
+ \ of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT\
67
+ \ AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\
68
+ \ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\
69
+ \ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\
70
+ \ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\
71
+ \ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\
72
+ \ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\
73
+ 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\
74
+ \ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\
75
+ \ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\
76
+ \ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\
77
+ \ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\
78
+ 5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\
79
+ \ and in connection with the Llama Materials, neither Meta nor Licensee may use\
80
+ \ any name or mark owned by or associated with the other or any of its affiliates,\
81
+ \ except as required for reasonable and customary use in describing and redistributing\
82
+ \ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\
83
+ \ a license to use “Llama 3” (the “Mark”) solely as required to comply with the\
84
+ \ last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently\
85
+ \ accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All\
86
+ \ goodwill arising out of your use of the Mark will inure to the benefit of Meta.\n\
87
+ b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for\
88
+ \ Meta, with respect to any derivative works and modifications of the Llama Materials\
89
+ \ that are made by you, as between you and Meta, you are and will be the owner of\
90
+ \ such derivative works and modifications.\nc. If you institute litigation or other\
91
+ \ proceedings against Meta or any entity (including a cross-claim or counterclaim\
92
+ \ in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results,\
93
+ \ or any portion of any of the foregoing, constitutes infringement of intellectual\
94
+ \ property or other rights owned or licensable by you, then any licenses granted\
95
+ \ to you under this Agreement shall terminate as of the date such litigation or\
96
+ \ claim is filed or instituted. You will indemnify and hold harmless Meta from and\
97
+ \ against any claim by any third party arising out of or related to your use or\
98
+ \ distribution of the Llama Materials.\n6. Term and Termination. The term of this\
99
+ \ Agreement will commence upon your acceptance of this Agreement or access to the\
100
+ \ Llama Materials and will continue in full force and effect until terminated in\
101
+ \ accordance with the terms and conditions herein. Meta may terminate this Agreement\
102
+ \ if you are in breach of any term or condition of this Agreement. Upon termination\
103
+ \ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
104
+ \ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
105
+ \ and Jurisdiction. This Agreement will be governed and construed under the laws\
106
+ \ of the State of California without regard to choice of law principles, and the\
107
+ \ UN Convention on Contracts for the International Sale of Goods does not apply\
108
+ \ to this Agreement. The courts of California shall have exclusive jurisdiction\
109
+ \ of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use\
110
+ \ Policy\nMeta is committed to promoting safe and fair use of its tools and features,\
111
+ \ including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable\
112
+ \ Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n\
113
+ #### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly.\
114
+ \ You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate\
115
+ \ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
116
+ \ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
117
+ \ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
118
+ \ or harm to children, including the solicitation, creation, acquisition, or dissemination\
119
+ \ of child exploitative content or failure to report Child Sexual Abuse Material\n\
120
+ \ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
121
+ \ illegal distribution of information or materials to minors, including obscene\
122
+ \ materials, or failure to employ legally required age-gating in connection with\
123
+ \ such information or materials.\n 5. Sexual solicitation\n 6. Any\
124
+ \ other criminal activity\n 2. Engage in, promote, incite, or facilitate the\
125
+ \ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
126
+ \ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\
127
+ \ or harmful conduct in the provision of employment, employment benefits, credit,\
128
+ \ housing, other economic benefits, or other essential goods and services\n 4.\
129
+ \ Engage in the unauthorized or unlicensed practice of any profession including,\
130
+ \ but not limited to, financial, legal, medical/health, or related professional\
131
+ \ practices\n 5. Collect, process, disclose, generate, or infer health, demographic,\
132
+ \ or other sensitive personal or private information about individuals without rights\
133
+ \ and consents required by applicable laws\n 6. Engage in or facilitate any action\
134
+ \ or generate any content that infringes, misappropriates, or otherwise violates\
135
+ \ any third-party rights, including the outputs or results of any products or services\
136
+ \ using the Llama Materials\n 7. Create, generate, or facilitate the creation\
137
+ \ of malicious code, malware, computer viruses or do anything else that could disable,\
138
+ \ overburden, interfere with or impair the proper working, integrity, operation\
139
+ \ or appearance of a website or computer system\n2. Engage in, promote, incite,\
140
+ \ facilitate, or assist in the planning or development of activities that present\
141
+ \ a risk of death or bodily harm to individuals, including use of Meta Llama 3 related\
142
+ \ to the following:\n 1. Military, warfare, nuclear industries or applications,\
143
+ \ espionage, use for materials or activities that are subject to the International\
144
+ \ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
145
+ \ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
146
+ \ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
147
+ \ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
148
+ \ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
149
+ \ content intended to incite or promote violence, abuse, or any infliction of bodily\
150
+ \ harm to an individual\n3. Intentionally deceive or mislead others, including use\
151
+ \ of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering\
152
+ \ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
153
+ \ or furthering defamatory content, including the creation of defamatory statements,\
154
+ \ images, or other content\n 3. Generating, promoting, or further distributing\
155
+ \ spam\n 4. Impersonating another individual without consent, authorization,\
156
+ \ or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are\
157
+ \ human-generated\n 6. Generating or facilitating false online engagement, including\
158
+ \ fake reviews and other means of fake online engagement\n4. Fail to appropriately\
159
+ \ disclose to end users any known dangers of your AI system\nPlease report any violation\
160
+ \ of this Policy, software “bug,” or other problems that could lead to a violation\
161
+ \ of this Policy through one of the following means:\n * Reporting issues with\
162
+ \ the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n\
163
+ \ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
164
+ \ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
165
+ \ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: LlamaUseReport@meta.com"
166
+ extra_gated_fields:
167
+ First Name: text
168
+ Last Name: text
169
+ Date of birth: date_picker
170
+ Country: country
171
+ Affiliation: text
172
+ geo: ip_location
173
+ ? By clicking Submit below I accept the terms of the license and acknowledge that
174
+ the information I provide will be collected stored processed and shared in accordance
175
+ with the Meta Privacy Policy
176
+ : checkbox
177
+ extra_gated_description: The information you provide will be collected, stored, processed
178
+ and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
179
+ extra_gated_button_content: Submit
180
+ base_model: pvbhanuteja/Meta-Llama-3-70B-Instruct
181
+ ---
182
+
183
+ <div style="width: auto; margin-left: auto; margin-right: auto">
184
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
185
+ </div>
186
+ <div style="display: flex; justify-content: space-between; width: 100%;">
187
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
188
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
189
+ Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
190
+ </p>
191
+ </div>
192
+ </div>
193
+
194
+ ## pvbhanuteja/Meta-Llama-3-70B-Instruct - GGUF
195
+
196
+ This repo contains GGUF format model files for [pvbhanuteja/Meta-Llama-3-70B-Instruct](https://huggingface.co/pvbhanuteja/Meta-Llama-3-70B-Instruct).
197
+
198
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
199
+
200
+ <div style="text-align: left; margin: 20px 0;">
201
+ <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
202
+ Run them on the TensorBlock client using your local machine ↗
203
+ </a>
204
+ </div>
205
+
206
+ ## Prompt template
207
+
208
+ ```
209
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
210
+
211
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
212
+
213
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
214
+ ```
215
+
216
+ ## Model file specification
217
+
218
+ | Filename | Quant type | File Size | Description |
219
+ | -------- | ---------- | --------- | ----------- |
220
+ | [Meta-Llama-3-70B-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q2_K.gguf) | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
221
+ | [Meta-Llama-3-70B-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q3_K_S.gguf) | Q3_K_S | 30.912 GB | very small, high quality loss |
222
+ | [Meta-Llama-3-70B-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q3_K_M.gguf) | Q3_K_M | 34.267 GB | very small, high quality loss |
223
+ | [Meta-Llama-3-70B-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q3_K_L.gguf) | Q3_K_L | 37.141 GB | small, substantial quality loss |
224
+ | [Meta-Llama-3-70B-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q4_0.gguf) | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
225
+ | [Meta-Llama-3-70B-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q4_K_S.gguf) | Q4_K_S | 40.347 GB | small, greater quality loss |
226
+ | [Meta-Llama-3-70B-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q4_K_M.gguf) | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
227
+ | [Meta-Llama-3-70B-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q5_0.gguf) | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
228
+ | [Meta-Llama-3-70B-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q5_K_S.gguf) | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
229
+ | [Meta-Llama-3-70B-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q5_K_M.gguf) | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
230
+ | [Meta-Llama-3-70B-Instruct-Q6_K](https://huggingface.co/tensorblock/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q6_K) | Q6_K | 57.888 GB | very large, extremely low quality loss |
231
+ | [Meta-Llama-3-70B-Instruct-Q8_0](https://huggingface.co/tensorblock/Meta-Llama-3-70B-Instruct-GGUF/blob/main/Meta-Llama-3-70B-Instruct-Q8_0) | Q8_0 | 74.975 GB | very large, extremely low quality loss - not recommended |
232
+
233
+
234
+ ## Downloading instruction
235
+
236
+ ### Command line
237
+
238
+ Firstly, install Huggingface Client
239
+
240
+ ```shell
241
+ pip install -U "huggingface_hub[cli]"
242
+ ```
243
+
244
+ Then, downoad the individual model file the a local directory
245
+
246
+ ```shell
247
+ huggingface-cli download tensorblock/Meta-Llama-3-70B-Instruct-GGUF --include "Meta-Llama-3-70B-Instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
248
+ ```
249
+
250
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
251
+
252
+ ```shell
253
+ huggingface-cli download tensorblock/Meta-Llama-3-70B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
254
+ ```