IntuitIntel
commited on
Commit
•
8eb26c6
1
Parent(s):
a6755c8
Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- README.md +218 -0
- config.json +46 -0
- model-00001-of-00085.safetensors +3 -0
- model-00002-of-00085.safetensors +3 -0
- model-00003-of-00085.safetensors +3 -0
- model-00004-of-00085.safetensors +3 -0
- model-00005-of-00085.safetensors +3 -0
- model-00006-of-00085.safetensors +3 -0
- model-00007-of-00085.safetensors +3 -0
- model-00008-of-00085.safetensors +3 -0
- model-00009-of-00085.safetensors +3 -0
- model-00010-of-00085.safetensors +3 -0
- model-00011-of-00085.safetensors +3 -0
- model-00012-of-00085.safetensors +3 -0
- model-00013-of-00085.safetensors +3 -0
- model-00014-of-00085.safetensors +3 -0
- model-00015-of-00085.safetensors +3 -0
- model-00016-of-00085.safetensors +3 -0
- model-00017-of-00085.safetensors +3 -0
- model-00018-of-00085.safetensors +3 -0
- model-00019-of-00085.safetensors +3 -0
- model-00020-of-00085.safetensors +3 -0
- model-00021-of-00085.safetensors +3 -0
- model-00022-of-00085.safetensors +3 -0
- model-00023-of-00085.safetensors +3 -0
- model-00024-of-00085.safetensors +3 -0
- model-00025-of-00085.safetensors +3 -0
- model-00026-of-00085.safetensors +3 -0
- model-00027-of-00085.safetensors +3 -0
- model-00028-of-00085.safetensors +3 -0
- model-00029-of-00085.safetensors +3 -0
- model-00030-of-00085.safetensors +3 -0
- model-00031-of-00085.safetensors +3 -0
- model-00032-of-00085.safetensors +3 -0
- model-00033-of-00085.safetensors +3 -0
- model-00034-of-00085.safetensors +3 -0
- model-00035-of-00085.safetensors +3 -0
- model-00036-of-00085.safetensors +3 -0
- model-00037-of-00085.safetensors +3 -0
- model-00038-of-00085.safetensors +3 -0
- model-00039-of-00085.safetensors +3 -0
- model-00040-of-00085.safetensors +3 -0
- model-00041-of-00085.safetensors +3 -0
- model-00042-of-00085.safetensors +3 -0
- model-00043-of-00085.safetensors +3 -0
- model-00044-of-00085.safetensors +3 -0
- model-00045-of-00085.safetensors +3 -0
- model-00046-of-00085.safetensors +3 -0
- model-00047-of-00085.safetensors +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,218 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- de
|
5 |
+
- fr
|
6 |
+
- it
|
7 |
+
- pt
|
8 |
+
- hi
|
9 |
+
- es
|
10 |
+
- th
|
11 |
+
library_name: transformers
|
12 |
+
base_model: meta-llama/Llama-3.1-405B-Instruct
|
13 |
+
license: llama3.1
|
14 |
+
pipeline_tag: text-generation
|
15 |
+
tags:
|
16 |
+
- facebook
|
17 |
+
- meta
|
18 |
+
- pytorch
|
19 |
+
- llama
|
20 |
+
- llama-3
|
21 |
+
- mlx
|
22 |
+
extra_gated_prompt: "### LLAMA 3.1 COMMUNITY LICENSE AGREEMENT\nLlama 3.1 Version\
|
23 |
+
\ Release Date: July 23, 2024\n\"Agreement\" means the terms and conditions for\
|
24 |
+
\ use, reproduction, distribution and modification of the Llama Materials set forth\
|
25 |
+
\ herein.\n\"Documentation\" means the specifications, manuals and documentation\
|
26 |
+
\ accompanying Llama 3.1 distributed by Meta at https://llama.meta.com/doc/overview.\n\
|
27 |
+
\"Licensee\" or \"you\" means you, or your employer or any other person or entity\
|
28 |
+
\ (if you are entering into this Agreement on such person or entity’s behalf), of\
|
29 |
+
\ the age required under applicable laws, rules or regulations to provide legal\
|
30 |
+
\ consent and that has legal authority to bind your employer or such other person\
|
31 |
+
\ or entity if you are entering in this Agreement on their behalf.\n\"Llama 3.1\"\
|
32 |
+
\ means the foundational large language models and software and algorithms, including\
|
33 |
+
\ machine-learning model code, trained model weights, inference-enabling code, training-enabling\
|
34 |
+
\ code, fine-tuning enabling code and other elements of the foregoing distributed\
|
35 |
+
\ by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means,\
|
36 |
+
\ collectively, Meta’s proprietary Llama 3.1 and Documentation (and any portion\
|
37 |
+
\ thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms\
|
38 |
+
\ Ireland Limited (if you are located in or, if you are an entity, your principal\
|
39 |
+
\ place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you\
|
40 |
+
\ are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\n\
|
41 |
+
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable\
|
42 |
+
\ and royalty-free limited license under Meta’s intellectual property or other rights\
|
43 |
+
\ owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy,\
|
44 |
+
\ create derivative works of, and make modifications to the Llama Materials.\nb.\
|
45 |
+
\ Redistribution and Use.\ni. If you distribute or make available the Llama Materials\
|
46 |
+
\ (or any derivative works thereof), or a product or service (including another\
|
47 |
+
\ AI model) that contains any of them, you shall (A) provide a copy of this Agreement\
|
48 |
+
\ with any such Llama Materials; and (B) prominently display “Built with Llama”\
|
49 |
+
\ on a related website, user interface, blogpost, about page, or product documentation.\
|
50 |
+
\ If you use the Llama Materials or any outputs or results of the Llama Materials\
|
51 |
+
\ to create, train, fine tune, or otherwise improve an AI model, which is distributed\
|
52 |
+
\ or made available, you shall also include “Llama” at the beginning of any such\
|
53 |
+
\ AI model name.\nii. If you receive Llama Materials, or any derivative works thereof,\
|
54 |
+
\ from a Licensee as part of an integrated end user product, then Section 2 of\
|
55 |
+
\ this Agreement will not apply to you.\niii. You must retain in all copies of the\
|
56 |
+
\ Llama Materials that you distribute the following attribution notice within a\
|
57 |
+
\ “Notice” text file distributed as a part of such copies: “Llama 3.1 is licensed\
|
58 |
+
\ under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights\
|
59 |
+
\ Reserved.”\niv. Your use of the Llama Materials must comply with applicable laws\
|
60 |
+
\ and regulations (including trade compliance laws and regulations) and adhere to\
|
61 |
+
\ the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3_1/use-policy),\
|
62 |
+
\ which is hereby incorporated by reference into this Agreement.\n2. Additional\
|
63 |
+
\ Commercial Terms. If, on the Llama 3.1 version release date, the monthly active\
|
64 |
+
\ users of the products or services made available by or for Licensee, or Licensee’s\
|
65 |
+
\ affiliates, is greater than 700 million monthly active users in the preceding\
|
66 |
+
\ calendar month, you must request a license from Meta, which Meta may grant to\
|
67 |
+
\ you in its sole discretion, and you are not authorized to exercise any of the\
|
68 |
+
\ rights under this Agreement unless or until Meta otherwise expressly grants you\
|
69 |
+
\ such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE\
|
70 |
+
\ LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS”\
|
71 |
+
\ BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY\
|
72 |
+
\ KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\
|
73 |
+
\ OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.\
|
74 |
+
\ YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING\
|
75 |
+
\ THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA\
|
76 |
+
\ MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT\
|
77 |
+
\ WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN\
|
78 |
+
\ CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS\
|
79 |
+
\ AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,\
|
80 |
+
\ EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED\
|
81 |
+
\ OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No\
|
82 |
+
\ trademark licenses are granted under this Agreement, and in connection with the\
|
83 |
+
\ Llama Materials, neither Meta nor Licensee may use any name or mark owned by or\
|
84 |
+
\ associated with the other or any of its affiliates, except as required for reasonable\
|
85 |
+
\ and customary use in describing and redistributing the Llama Materials or as set\
|
86 |
+
\ forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the\
|
87 |
+
\ “Mark”) solely as required to comply with the last sentence of Section 1.b.i.\
|
88 |
+
\ You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/\
|
89 |
+
\ ). All goodwill arising out of your use of the Mark will inure to the benefit\
|
90 |
+
\ of Meta.\nb. Subject to Meta’s ownership of Llama Materials and derivatives made\
|
91 |
+
\ by or for Meta, with respect to any derivative works and modifications of the\
|
92 |
+
\ Llama Materials that are made by you, as between you and Meta, you are and will\
|
93 |
+
\ be the owner of such derivative works and modifications.\nc. If you institute\
|
94 |
+
\ litigation or other proceedings against Meta or any entity (including a cross-claim\
|
95 |
+
\ or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.1 outputs\
|
96 |
+
\ or results, or any portion of any of the foregoing, constitutes infringement of\
|
97 |
+
\ intellectual property or other rights owned or licensable by you, then any licenses\
|
98 |
+
\ granted to you under this Agreement shall terminate as of the date such litigation\
|
99 |
+
\ or claim is filed or instituted. You will indemnify and hold harmless Meta from\
|
100 |
+
\ and against any claim by any third party arising out of or related to your use\
|
101 |
+
\ or distribution of the Llama Materials.\n6. Term and Termination. The term of\
|
102 |
+
\ this Agreement will commence upon your acceptance of this Agreement or access\
|
103 |
+
\ to the Llama Materials and will continue in full force and effect until terminated\
|
104 |
+
\ in accordance with the terms and conditions herein. Meta may terminate this Agreement\
|
105 |
+
\ if you are in breach of any term or condition of this Agreement. Upon termination\
|
106 |
+
\ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
|
107 |
+
\ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
|
108 |
+
\ and Jurisdiction. This Agreement will be governed and construed under the laws\
|
109 |
+
\ of the State of California without regard to choice of law principles, and the\
|
110 |
+
\ UN Convention on Contracts for the International Sale of Goods does not apply\
|
111 |
+
\ to this Agreement. The courts of California shall have exclusive jurisdiction\
|
112 |
+
\ of any dispute arising out of this Agreement.\n### Llama 3.1 Acceptable Use Policy\n\
|
113 |
+
Meta is committed to promoting safe and fair use of its tools and features, including\
|
114 |
+
\ Llama 3.1. If you access or use Llama 3.1, you agree to this Acceptable Use Policy\
|
115 |
+
\ (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3_1/use-policy](https://llama.meta.com/llama3_1/use-policy)\n\
|
116 |
+
#### Prohibited Uses\nWe want everyone to use Llama 3.1 safely and responsibly.\
|
117 |
+
\ You agree you will not use, or allow others to use, Llama 3.1 to:\n 1. Violate\
|
118 |
+
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
|
119 |
+
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
|
120 |
+
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
|
121 |
+
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
|
122 |
+
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
|
123 |
+
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
|
124 |
+
\ illegal distribution of information or materials to minors, including obscene\
|
125 |
+
\ materials, or failure to employ legally required age-gating in connection with\
|
126 |
+
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
|
127 |
+
\ other criminal activity\n 3. Engage in, promote, incite, or facilitate the\
|
128 |
+
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
|
129 |
+
\ 4. Engage in, promote, incite, or facilitate discrimination or other unlawful\
|
130 |
+
\ or harmful conduct in the provision of employment, employment benefits, credit,\
|
131 |
+
\ housing, other economic benefits, or other essential goods and services\n 5.\
|
132 |
+
\ Engage in the unauthorized or unlicensed practice of any profession including,\
|
133 |
+
\ but not limited to, financial, legal, medical/health, or related professional\
|
134 |
+
\ practices\n 6. Collect, process, disclose, generate, or infer health, demographic,\
|
135 |
+
\ or other sensitive personal or private information about individuals without rights\
|
136 |
+
\ and consents required by applicable laws\n 7. Engage in or facilitate any action\
|
137 |
+
\ or generate any content that infringes, misappropriates, or otherwise violates\
|
138 |
+
\ any third-party rights, including the outputs or results of any products or services\
|
139 |
+
\ using the Llama Materials\n 8. Create, generate, or facilitate the creation\
|
140 |
+
\ of malicious code, malware, computer viruses or do anything else that could disable,\
|
141 |
+
\ overburden, interfere with or impair the proper working, integrity, operation\
|
142 |
+
\ or appearance of a website or computer system\n2. Engage in, promote, incite,\
|
143 |
+
\ facilitate, or assist in the planning or development of activities that present\
|
144 |
+
\ a risk of death or bodily harm to individuals, including use of Llama 3.1 related\
|
145 |
+
\ to the following:\n 1. Military, warfare, nuclear industries or applications,\
|
146 |
+
\ espionage, use for materials or activities that are subject to the International\
|
147 |
+
\ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
|
148 |
+
\ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
|
149 |
+
\ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
|
150 |
+
\ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
|
151 |
+
\ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
|
152 |
+
\ content intended to incite or promote violence, abuse, or any infliction of bodily\
|
153 |
+
\ harm to an individual\n3. Intentionally deceive or mislead others, including use\
|
154 |
+
\ of Llama 3.1 related to the following:\n 1. Generating, promoting, or furthering\
|
155 |
+
\ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
|
156 |
+
\ or furthering defamatory content, including the creation of defamatory statements,\
|
157 |
+
\ images, or other content\n 3. Generating, promoting, or further distributing\
|
158 |
+
\ spam\n 4. Impersonating another individual without consent, authorization,\
|
159 |
+
\ or legal right\n 5. Representing that the use of Llama 3.1 or outputs are human-generated\n\
|
160 |
+
\ 6. Generating or facilitating false online engagement, including fake reviews\
|
161 |
+
\ and other means of fake online engagement\n4. Fail to appropriately disclose to\
|
162 |
+
\ end users any known dangers of your AI system\nPlease report any violation of\
|
163 |
+
\ this Policy, software “bug,” or other problems that could lead to a violation\
|
164 |
+
\ of this Policy through one of the following means:\n * Reporting issues with\
|
165 |
+
\ the model: [https://github.com/meta-llama/llama-models/issues](https://github.com/meta-llama/llama-models/issues)\n\
|
166 |
+
\ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
|
167 |
+
\ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
|
168 |
+
\ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: LlamaUseReport@meta.com"
|
169 |
+
extra_gated_fields:
|
170 |
+
First Name: text
|
171 |
+
Last Name: text
|
172 |
+
Date of birth: date_picker
|
173 |
+
Country: country
|
174 |
+
Affiliation: text
|
175 |
+
Job title:
|
176 |
+
type: select
|
177 |
+
options:
|
178 |
+
- Student
|
179 |
+
- Research Graduate
|
180 |
+
- AI researcher
|
181 |
+
- AI developer/engineer
|
182 |
+
- Reporter
|
183 |
+
- Other
|
184 |
+
geo: ip_location
|
185 |
+
? By clicking Submit below I accept the terms of the license and acknowledge that
|
186 |
+
the information I provide will be collected stored processed and shared in accordance
|
187 |
+
with the Meta Privacy Policy
|
188 |
+
: checkbox
|
189 |
+
extra_gated_description: The information you provide will be collected, stored, processed
|
190 |
+
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
|
191 |
+
extra_gated_button_content: Submit
|
192 |
+
---
|
193 |
+
|
194 |
+
# mlx-community/Meta-Llama-3.1-405B-Instruct-8bit
|
195 |
+
|
196 |
+
The Model [mlx-community/Meta-Llama-3.1-405B-Instruct-8bit](https://huggingface.co/mlx-community/Meta-Llama-3.1-405B-Instruct-8bit) was converted to MLX format from [meta-llama/Llama-3.1-405B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct) using mlx-lm version **0.19.3**.
|
197 |
+
|
198 |
+
## Use with mlx
|
199 |
+
|
200 |
+
```bash
|
201 |
+
pip install mlx-lm
|
202 |
+
```
|
203 |
+
|
204 |
+
```python
|
205 |
+
from mlx_lm import load, generate
|
206 |
+
|
207 |
+
model, tokenizer = load("mlx-community/Meta-Llama-3.1-405B-Instruct-8bit")
|
208 |
+
|
209 |
+
prompt="hello"
|
210 |
+
|
211 |
+
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
|
212 |
+
messages = [{"role": "user", "content": prompt}]
|
213 |
+
prompt = tokenizer.apply_chat_template(
|
214 |
+
messages, tokenize=False, add_generation_prompt=True
|
215 |
+
)
|
216 |
+
|
217 |
+
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
218 |
+
```
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 128000,
|
8 |
+
"eos_token_id": [
|
9 |
+
128001,
|
10 |
+
128008,
|
11 |
+
128009
|
12 |
+
],
|
13 |
+
"hidden_act": "silu",
|
14 |
+
"hidden_size": 16384,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 53248,
|
17 |
+
"max_position_embeddings": 131072,
|
18 |
+
"mlp_bias": false,
|
19 |
+
"model_type": "llama",
|
20 |
+
"num_attention_heads": 128,
|
21 |
+
"num_hidden_layers": 126,
|
22 |
+
"num_key_value_heads": 8,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"quantization": {
|
25 |
+
"group_size": 64,
|
26 |
+
"bits": 8
|
27 |
+
},
|
28 |
+
"quantization_config": {
|
29 |
+
"group_size": 64,
|
30 |
+
"bits": 8
|
31 |
+
},
|
32 |
+
"rms_norm_eps": 1e-05,
|
33 |
+
"rope_scaling": {
|
34 |
+
"factor": 8.0,
|
35 |
+
"high_freq_factor": 4.0,
|
36 |
+
"low_freq_factor": 1.0,
|
37 |
+
"original_max_position_embeddings": 8192,
|
38 |
+
"rope_type": "llama3"
|
39 |
+
},
|
40 |
+
"rope_theta": 500000.0,
|
41 |
+
"tie_word_embeddings": false,
|
42 |
+
"torch_dtype": "bfloat16",
|
43 |
+
"transformers_version": "4.43.3",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 128256
|
46 |
+
}
|
model-00001-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30384a8b3b0952954eada7444bc01b447667adb23bcebf52000ee5be3593bc3c
|
3 |
+
size 4692642146
|
model-00002-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e2a53541e8682c54efc40645397b22fb71eadc3b98368826f7757162d3b7c19
|
3 |
+
size 4920054237
|
model-00003-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bf622fcea87e94b6e9aa8948586a947fec7b5b72e502c5260f52b11b07c26d2
|
3 |
+
size 5240851727
|
model-00004-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdf5d68efc3d4107aaef8693b396333352b069b739cda553e4f677c8f6f2e84f
|
3 |
+
size 4920054251
|
model-00005-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c49231a16fac2d37f3acb18c723bd6468381a179551ffb667b3b7c324920f4ce
|
3 |
+
size 5240851721
|
model-00006-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7abc76ea1b9c71e64605068767838165426e8392e9deb7469a1ebafcdce3d4a4
|
3 |
+
size 4920054239
|
model-00007-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d9d53f986a87d7e2af7903a7842663b31356e1750d8853d80bc3f9da7b80f77
|
3 |
+
size 5240851719
|
model-00008-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16067a2a04ac0fc4e0f1a65bfa237ba7b0892cdd355339298ab08a8f8ab7bdc7
|
3 |
+
size 4920054272
|
model-00009-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ff78029ac36838f9d1f2c90479ec0173ff3b03542b91fb54437e4c6012827c0
|
3 |
+
size 5240851748
|
model-00010-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71cf9ddffe57d00582b909c1e5e5a2acb5aedc04ef233e979005f175e35343e4
|
3 |
+
size 4920054305
|
model-00011-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8521a93c0c7f4b54739bed39110d4ec838ee24d13236799ef72c8438db9fcdef
|
3 |
+
size 5240851752
|
model-00012-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6b9a176e7aa247c464d368b24f7196cf7f4683d10b4b1fe0381cbe0caa5cfb8
|
3 |
+
size 4920054305
|
model-00013-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30d6385a6f2136105f19a72a6c0887557f5c8fa2e50d6418c124781b32481b42
|
3 |
+
size 5240851756
|
model-00014-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:214ad08a846cee60461aca5f7dc6a9146dc7d5c51aaf0556f754741e650b9c4b
|
3 |
+
size 4920054285
|
model-00015-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b72ba49a03d1b3f2434b0f8e49a315d15a24121c5441393543e29b58424c661
|
3 |
+
size 5240851754
|
model-00016-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:037f9ae5fa4c17786931e281352f0b99444925ea79ca91aedfbdaeeec1fa3608
|
3 |
+
size 4920054299
|
model-00017-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfefa2fede9afa524576cee310a2a199e4b754741fc4554206ec2544290ccf4d
|
3 |
+
size 5240851742
|
model-00018-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:357c8bbdd9e2041d07b5e2039d7a9363439faefa2097b85609ad948010e23cd2
|
3 |
+
size 4920054287
|
model-00019-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1db0d7517f9a50fe53c610a9a27ed2332d9b1561b45a28ba6a3284fb817759a0
|
3 |
+
size 5240851742
|
model-00020-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95c85a08434f0076ad6798d1280e872eb3a22a4ddbf0c74153dfde80dd1d9518
|
3 |
+
size 4920054303
|
model-00021-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bac6df81cab98d0eabd4c458596068857cd85d82cc73d7eec268f43b5c920f3c
|
3 |
+
size 5240851748
|
model-00022-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d244d8158e2b5cb6c5e1d3dc4d4e30d96b8370b9188ebba1a0313ee23e220663
|
3 |
+
size 4920054295
|
model-00023-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:011e88d862af2cb7ff4ff42d5f286a88aedb839d9ac7aa4a0f6d7179c2f8c1d0
|
3 |
+
size 5240851718
|
model-00024-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6aedca0cffc1f823896d6f6e9baf8c3e21f37d26722552057233d258a8eaea1d
|
3 |
+
size 4920054277
|
model-00025-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97ce4cd15cd717a10c012ba333ef9b084169984af773a228a79bc02d1dde31d7
|
3 |
+
size 5240851748
|
model-00026-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:939586e0aa81d0ff160a438c9c55b868afaf74e5e5f71d874f84a4dad9c10c9d
|
3 |
+
size 4920054299
|
model-00027-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce77d29930d3a5563b9803c3b83f851a7ff80999e35055e2baa314ad6fcdf4ad
|
3 |
+
size 5240851752
|
model-00028-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa84520aacdc1f5d9c8e6c4b9538e0798e19a4185d7157f79e0b564c4105580c
|
3 |
+
size 4920054293
|
model-00029-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4088232f1a436445b68852ad0c6156d3d7ad8d9e2d67903d1e7a373f5860b2fe
|
3 |
+
size 5240851758
|
model-00030-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:884d63eba3e5d0473c109398a39afec40fce192dc76a0be104fd4c52a24c9d6d
|
3 |
+
size 4920054303
|
model-00031-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c6c50aba95bbb1f789482dadfc49cdf94fe473509d4ed928d8ec61b2015d7f8
|
3 |
+
size 5240851754
|
model-00032-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d8034cc3a6d97320cc47f2b14378e0ac275498c2f1694535a0d6a1fa726f27b
|
3 |
+
size 4920054293
|
model-00033-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28d3dd1b082981b42cad3ac48fcaa6bcad3828a243710afe1e204c500adf6077
|
3 |
+
size 5240851736
|
model-00034-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:425fb0b396fd8eaa2b07074b6167a6208473d96b6d5baec3302f51784caacbcf
|
3 |
+
size 4920054297
|
model-00035-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0306d34be6816ccc9aa9b799eaf4dd868c344d6c66038cf5766840064fa78939
|
3 |
+
size 5240851738
|
model-00036-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3166c9fab9ea51010ce4f032046452d369e91b83e0a0e732661b2ec7ab993b37
|
3 |
+
size 4920054307
|
model-00037-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc4dcb3881237bd5f4e790bad14198c18a47e5984e680d90adfd9523fc40e434
|
3 |
+
size 5240851740
|
model-00038-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de9b7ad4c3f699ba4b748cdd9e7ebf9e06f53350b3b970fb8b85a196f3980ec9
|
3 |
+
size 4920054295
|
model-00039-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d273dafdb32ace293e303c03b15661c30e3332869fa3e1994f4c958d231f940
|
3 |
+
size 5240851744
|
model-00040-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dac485160ae8dbcc3e9bdde65977c80e6970fd25f63ff5472003cf578de8ca7e
|
3 |
+
size 4920054287
|
model-00041-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02be49d042a2713e366b9ece55512bbe40330455cf8d115f0578e59f9b4904e1
|
3 |
+
size 5240851746
|
model-00042-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55269c808b38f98630a2202ea197cbc463a26062af497fa9905e5de7b4213537
|
3 |
+
size 4920054285
|
model-00043-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21fe289e6e828c73eb8f67bfe32f764916aee4366b1e7d854a2dfdbec99da885
|
3 |
+
size 5240851734
|
model-00044-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfaa1859192e341f9a3b3ae08a8e606a3c3c1d341c7a46207efb207d0832fb08
|
3 |
+
size 4920054295
|
model-00045-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bf31ebc92475ebcf4eac0173d60fc22caf319ed18400a44175400cec361f61c
|
3 |
+
size 5240851758
|
model-00046-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fa85fda28e19ffe73bed3520318ca3bb9d2fa6d77f5940107df8f301bcfc10e
|
3 |
+
size 4920054283
|
model-00047-of-00085.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d19b9ebdbee901296016886af8bebeb59e8c5fd94c90a7e37fe7614edf60000
|
3 |
+
size 5240851750
|