Commit
·
89318ba
1
Parent(s):
09e24a3
Add files using upload-large-folder tool
Browse files- README.md +224 -45
- config.json +8 -0
- model.safetensors.index.json +649 -255
- tokenizer_config.json +1 -0
README.md
CHANGED
|
@@ -1,58 +1,237 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
tags:
|
| 4 |
-
- reasoning
|
| 5 |
-
- llama
|
| 6 |
-
- deepseek
|
| 7 |
-
- ollama
|
| 8 |
-
- chain-of-thoughts
|
| 9 |
-
- small-llm
|
| 10 |
-
- edge
|
| 11 |
language:
|
| 12 |
- en
|
| 13 |
-
|
| 14 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
---
|
| 16 |
|
| 17 |
-
#
|
| 18 |
-
|
| 19 |
-
HF: https://huggingface.co/adeelahmad/ReasonableLlama3-3B-Jr
|
| 20 |
-
Ollama: https://ollama.com/adeelahmad/ReasonableLLAMA-Jr-3b
|
| 21 |
-
|
| 22 |
-
Welcome to **ReasonableLlama-3B**, a cutting-edge reasoning model built on the foundation of LLaMA-3B. This model has been carefully fine-tuned to enhance its capabilities in logical
|
| 23 |
-
thinking, problem-solving, and creative analysis.
|
| 24 |
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
- **Purpose**: Designed for tasks requiring advanced reasoning, problem-solving, and creative thinking
|
| 29 |
|
| 30 |
-
##
|
| 31 |
-
- **Advanced Reasoning**: Excels in logical analysis, problem-solving, and decision-making.
|
| 32 |
-
- **Creative Thinking**: Generates innovative solutions and ideas.
|
| 33 |
-
- **Curriculum-Based Fine-Tuning**: Trained on high-quality datasets to enhance reasoning abilities.
|
| 34 |
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
- **Specialization**: Optimized for specific reasoning workflows and scenarios
|
| 39 |
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
- **Education**: Assists in creating educational examples and problem sets.
|
| 43 |
-
- **Problem Solving**: Helps generate innovative solutions across various domains.
|
| 44 |
|
| 45 |
-
|
| 46 |
-
- **Integration**: Can be integrated into existing systems via APIs or local setup.
|
| 47 |
-
- **Inputs**: Supports text and images, leveraging Ollama's versatile capabilities.
|
| 48 |
|
| 49 |
-
|
| 50 |
-
- **Scope**: Limited to single-step reasoning; multi-hop reasoning is a current focus area.
|
| 51 |
-
- **Data Bias**: Caution with dataset provenance as it may reflect historical biases.
|
| 52 |
|
| 53 |
-
|
| 54 |
-
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
- Acknowledgments to the community contributing to open-source AI advancements.
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: mlx-community/Llama-3.2-3B-Instruct
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
+
- de
|
| 6 |
+
- fr
|
| 7 |
+
- it
|
| 8 |
+
- pt
|
| 9 |
+
- hi
|
| 10 |
+
- es
|
| 11 |
+
- th
|
| 12 |
+
library_name: transformers
|
| 13 |
+
license: llama3.2
|
| 14 |
+
pipeline_tag: text-generation
|
| 15 |
+
tags:
|
| 16 |
+
- facebook
|
| 17 |
+
- meta
|
| 18 |
+
- pytorch
|
| 19 |
+
- llama
|
| 20 |
+
- llama-3
|
| 21 |
+
- mlx
|
| 22 |
+
- mlx
|
| 23 |
+
extra_gated_prompt: "### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\n\nLlama 3.2 Version\
|
| 24 |
+
\ Release Date: September 25, 2024\n\n“Agreement” means the terms and conditions\
|
| 25 |
+
\ for use, reproduction, distribution and modification of the Llama Materials set\
|
| 26 |
+
\ forth herein.\n\n“Documentation” means the specifications, manuals and documentation\
|
| 27 |
+
\ accompanying Llama 3.2 distributed by Meta at https://llama.meta.com/doc/overview.\n\
|
| 28 |
+
\n“Licensee” or “you” means you, or your employer or any other person or entity\
|
| 29 |
+
\ (if you are entering into this Agreement on such person or entity’s behalf),\
|
| 30 |
+
\ of the age required under applicable laws, rules or regulations to provide legal\
|
| 31 |
+
\ consent and that has legal authority to bind your employer or such other person\
|
| 32 |
+
\ or entity if you are entering in this Agreement on their behalf.\n\n“Llama 3.2”\
|
| 33 |
+
\ means the foundational large language models and software and algorithms, including\
|
| 34 |
+
\ machine-learning model code, trained model weights, inference-enabling code, training-enabling\
|
| 35 |
+
\ code, fine-tuning enabling code and other elements of the foregoing distributed\
|
| 36 |
+
\ by Meta at https://www.llama.com/llama-downloads.\n\n“Llama Materials” means,\
|
| 37 |
+
\ collectively, Meta’s proprietary Llama 3.2 and Documentation (and any portion\
|
| 38 |
+
\ thereof) made available under this Agreement.\n\n“Meta” or “we” means Meta Platforms\
|
| 39 |
+
\ Ireland Limited (if you are located in or, if you are an entity, your principal\
|
| 40 |
+
\ place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if\
|
| 41 |
+
\ you are located outside of the EEA or Switzerland). \n\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.\n\n1. License Rights and Redistribution.\n\
|
| 44 |
+
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable\
|
| 45 |
+
\ and 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,\
|
| 47 |
+
\ copy, create derivative works of, and make modifications to the Llama Materials.\
|
| 48 |
+
\ \nb. Redistribution and Use. \ni. If you distribute or make available the Llama\
|
| 49 |
+
\ Materials (or any derivative works thereof), or a product or service (including\
|
| 50 |
+
\ another AI model) that contains any of them, you shall (A) provide a copy of this\
|
| 51 |
+
\ Agreement with any such Llama Materials; and (B) prominently display “Built with\
|
| 52 |
+
\ Llama” on a related website, user interface, blogpost, about page, or product\
|
| 53 |
+
\ documentation. If you use the Llama Materials or any outputs or results of the\
|
| 54 |
+
\ Llama Materials to create, train, fine tune, or otherwise improve an AI model,\
|
| 55 |
+
\ which is distributed or made available, you shall also include “Llama” at the\
|
| 56 |
+
\ beginning of any such AI model name.\nii. If you receive Llama Materials, or any\
|
| 57 |
+
\ derivative works thereof, from a Licensee as part of an integrated end user product,\
|
| 58 |
+
\ then Section 2 of this Agreement will not apply to you. \niii. You must retain\
|
| 59 |
+
\ in all copies of the Llama Materials that you distribute the following attribution\
|
| 60 |
+
\ notice within a “Notice” text file distributed as a part of such copies: “Llama\
|
| 61 |
+
\ 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,\
|
| 62 |
+
\ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
|
| 63 |
+
\ applicable laws and regulations (including trade compliance laws and regulations)\
|
| 64 |
+
\ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
|
| 65 |
+
\ https://www.llama.com/llama3_2/use-policy), which is hereby incorporated by reference\
|
| 66 |
+
\ into this Agreement.\n \n2. Additional Commercial Terms. If, on the Llama 3.2\
|
| 67 |
+
\ version release date, the monthly active users of the products or services made\
|
| 68 |
+
\ available by or for Licensee, or Licensee’s affiliates, is greater than 700 million\
|
| 69 |
+
\ monthly active users in the preceding calendar month, you must request a license\
|
| 70 |
+
\ from Meta, which Meta may grant to you in its sole discretion, and you are not\
|
| 71 |
+
\ authorized to exercise any of the rights under this Agreement unless or until\
|
| 72 |
+
\ Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS\
|
| 73 |
+
\ REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM\
|
| 74 |
+
\ ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS\
|
| 75 |
+
\ ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION,\
|
| 76 |
+
\ ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR\
|
| 77 |
+
\ PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING\
|
| 78 |
+
\ OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR\
|
| 79 |
+
\ USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability.\
|
| 80 |
+
\ IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,\
|
| 81 |
+
\ WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\
|
| 82 |
+
\ OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\
|
| 83 |
+
\ INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE\
|
| 84 |
+
\ BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\n\
|
| 85 |
+
a. No trademark licenses are granted under this Agreement, and in connection with\
|
| 86 |
+
\ the Llama Materials, neither Meta nor Licensee may use any name or mark owned\
|
| 87 |
+
\ by or associated with the other or any of its affiliates, except as required\
|
| 88 |
+
\ for reasonable and customary use in describing and redistributing the Llama Materials\
|
| 89 |
+
\ or as set forth in this Section 5(a). Meta hereby grants you a license to use\
|
| 90 |
+
\ “Llama” (the “Mark”) solely as required to comply with the last sentence of Section\
|
| 91 |
+
\ 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at\
|
| 92 |
+
\ https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising\
|
| 93 |
+
\ out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to\
|
| 94 |
+
\ Meta’s ownership of Llama Materials and derivatives made by or for Meta, with\
|
| 95 |
+
\ respect to any derivative works and modifications of the Llama Materials that\
|
| 96 |
+
\ are made by you, as between you and Meta, you are and will be the owner of such\
|
| 97 |
+
\ derivative works and modifications.\nc. If you institute litigation or other proceedings\
|
| 98 |
+
\ against Meta or any entity (including a cross-claim or counterclaim in a lawsuit)\
|
| 99 |
+
\ alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion\
|
| 100 |
+
\ of any of the foregoing, constitutes infringement of intellectual property or\
|
| 101 |
+
\ other rights owned or licensable by you, then any licenses granted to you under\
|
| 102 |
+
\ this Agreement shall terminate as of the date such litigation or claim is filed\
|
| 103 |
+
\ or instituted. You will indemnify and hold harmless Meta from and against any\
|
| 104 |
+
\ claim by any third party arising out of or related to your use or distribution\
|
| 105 |
+
\ of the Llama Materials.\n6. Term and Termination. The term of this Agreement will\
|
| 106 |
+
\ commence upon your acceptance of this Agreement or access to the Llama Materials\
|
| 107 |
+
\ and will continue in full force and effect until terminated in accordance with\
|
| 108 |
+
\ the terms and conditions herein. Meta may terminate this Agreement if you are\
|
| 109 |
+
\ in breach of any term or condition of this Agreement. Upon termination of this\
|
| 110 |
+
\ Agreement, you shall delete and cease use of the Llama Materials. Sections 3,\
|
| 111 |
+
\ 4 and 7 shall survive the termination of this Agreement. \n7. Governing Law and\
|
| 112 |
+
\ Jurisdiction. This Agreement will be governed and construed under the laws of\
|
| 113 |
+
\ the State of California without regard to choice of law principles, and the UN\
|
| 114 |
+
\ Convention on Contracts for the International Sale of Goods does not apply to\
|
| 115 |
+
\ this Agreement. The courts of California shall have exclusive jurisdiction of\
|
| 116 |
+
\ any dispute arising out of this Agreement. \n### Llama 3.2 Acceptable Use Policy\n\
|
| 117 |
+
Meta is committed to promoting safe and fair use of its tools and features, including\
|
| 118 |
+
\ Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy\
|
| 119 |
+
\ (“**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\
|
| 120 |
+
#### Prohibited Uses\nWe want everyone to use Llama 3.2 safely and responsibly.\
|
| 121 |
+
\ You agree you will not use, or allow others to use, Llama 3.2 to:\n1. Violate\
|
| 122 |
+
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
|
| 123 |
+
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
|
| 124 |
+
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
|
| 125 |
+
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
|
| 126 |
+
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
|
| 127 |
+
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
|
| 128 |
+
\ illegal distribution of information or materials to minors, including obscene\
|
| 129 |
+
\ materials, or failure to employ legally required age-gating in connection with\
|
| 130 |
+
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
|
| 131 |
+
\ other criminal activity\n 1. Engage in, promote, incite, or facilitate the\
|
| 132 |
+
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
|
| 133 |
+
\ 2. Engage in, promote, incite, or facilitate discrimination or other unlawful\
|
| 134 |
+
\ or harmful conduct in the provision of employment, employment benefits, credit,\
|
| 135 |
+
\ housing, other economic benefits, or other essential goods and services\n 3.\
|
| 136 |
+
\ Engage in the unauthorized or unlicensed practice of any profession including,\
|
| 137 |
+
\ but not limited to, financial, legal, medical/health, or related professional\
|
| 138 |
+
\ practices\n 4. Collect, process, disclose, generate, or infer private or sensitive\
|
| 139 |
+
\ information about individuals, including information about individuals’ identity,\
|
| 140 |
+
\ health, or demographic information, unless you have obtained the right to do so\
|
| 141 |
+
\ in accordance with applicable law\n 5. Engage in or facilitate any action or\
|
| 142 |
+
\ generate any content that infringes, misappropriates, or otherwise violates any\
|
| 143 |
+
\ third-party rights, including the outputs or results of any products or services\
|
| 144 |
+
\ using the Llama Materials\n 6. Create, generate, or facilitate the creation\
|
| 145 |
+
\ of malicious code, malware, computer viruses or do anything else that could disable,\
|
| 146 |
+
\ overburden, interfere with or impair the proper working, integrity, operation\
|
| 147 |
+
\ or appearance of a website or computer system\n 7. Engage in any action, or\
|
| 148 |
+
\ facilitate any action, to intentionally circumvent or remove usage restrictions\
|
| 149 |
+
\ or other safety measures, or to enable functionality disabled by Meta \n2. Engage\
|
| 150 |
+
\ in, promote, incite, facilitate, or assist in the planning or development of activities\
|
| 151 |
+
\ that present a risk of death or bodily harm to individuals, including use of Llama\
|
| 152 |
+
\ 3.2 related to the following:\n 8. Military, warfare, nuclear industries or\
|
| 153 |
+
\ applications, espionage, use for materials or activities that are subject to the\
|
| 154 |
+
\ International Traffic Arms Regulations (ITAR) maintained by the United States\
|
| 155 |
+
\ Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989\
|
| 156 |
+
\ or the Chemical Weapons Convention Implementation Act of 1997\n 9. Guns and\
|
| 157 |
+
\ illegal weapons (including weapon development)\n 10. Illegal drugs and regulated/controlled\
|
| 158 |
+
\ substances\n 11. Operation of critical infrastructure, transportation technologies,\
|
| 159 |
+
\ or heavy machinery\n 12. Self-harm or harm to others, including suicide, cutting,\
|
| 160 |
+
\ and eating disorders\n 13. Any content intended to incite or promote violence,\
|
| 161 |
+
\ abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive\
|
| 162 |
+
\ or mislead others, including use of Llama 3.2 related to the following:\n 14.\
|
| 163 |
+
\ Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\
|
| 164 |
+
\ 15. Generating, promoting, or furthering defamatory content, including the\
|
| 165 |
+
\ creation of defamatory statements, images, or other content\n 16. Generating,\
|
| 166 |
+
\ promoting, or further distributing spam\n 17. Impersonating another individual\
|
| 167 |
+
\ without consent, authorization, or legal right\n 18. Representing that the\
|
| 168 |
+
\ use of Llama 3.2 or outputs are human-generated\n 19. Generating or facilitating\
|
| 169 |
+
\ false online engagement, including fake reviews and other means of fake online\
|
| 170 |
+
\ engagement \n4. Fail to appropriately disclose to end users any known dangers\
|
| 171 |
+
\ of your AI system 5. Interact with third party tools, models, or software designed\
|
| 172 |
+
\ to generate unlawful content or engage in unlawful or harmful conduct and/or represent\
|
| 173 |
+
\ that the outputs of such tools, models, or software are associated with Meta or\
|
| 174 |
+
\ Llama 3.2\n\nWith respect to any multimodal models included in Llama 3.2, the\
|
| 175 |
+
\ rights granted under Section 1(a) of the Llama 3.2 Community License Agreement\
|
| 176 |
+
\ are not being granted to you if you are an individual domiciled in, or a company\
|
| 177 |
+
\ with a principal place of business in, the European Union. This restriction does\
|
| 178 |
+
\ not apply to end users of a product or service that incorporates any such multimodal\
|
| 179 |
+
\ models.\n\nPlease report any violation of this Policy, software “bug,” or other\
|
| 180 |
+
\ problems that could lead to a violation of this Policy through one of the following\
|
| 181 |
+
\ 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\
|
| 182 |
+
* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\n\
|
| 183 |
+
* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\n\
|
| 184 |
+
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama\
|
| 185 |
+
\ 3.2: [email protected]"
|
| 186 |
+
extra_gated_fields:
|
| 187 |
+
First Name: text
|
| 188 |
+
Last Name: text
|
| 189 |
+
Date of birth: date_picker
|
| 190 |
+
Country: country
|
| 191 |
+
Affiliation: text
|
| 192 |
+
Job title:
|
| 193 |
+
type: select
|
| 194 |
+
options:
|
| 195 |
+
- Student
|
| 196 |
+
- Research Graduate
|
| 197 |
+
- AI researcher
|
| 198 |
+
- AI developer/engineer
|
| 199 |
+
- Reporter
|
| 200 |
+
- Other
|
| 201 |
+
geo: ip_location
|
| 202 |
+
? By clicking Submit below I accept the terms of the license and acknowledge that
|
| 203 |
+
the information I provide will be collected stored processed and shared in accordance
|
| 204 |
+
with the Meta Privacy Policy
|
| 205 |
+
: checkbox
|
| 206 |
+
extra_gated_description: The information you provide will be collected, stored, processed
|
| 207 |
+
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
|
| 208 |
+
extra_gated_button_content: Submit
|
| 209 |
---
|
| 210 |
|
| 211 |
+
# adeelahmad/ReasonableLlama3-3B-Jr
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 212 |
|
| 213 |
+
The Model [adeelahmad/ReasonableLlama3-3B-Jr](https://huggingface.co/adeelahmad/ReasonableLlama3-3B-Jr) was
|
| 214 |
+
converted to MLX format from [mlx-community/Llama-3.2-3B-Instruct](https://huggingface.co/mlx-community/Llama-3.2-3B-Instruct)
|
| 215 |
+
using mlx-lm version **0.21.4**.
|
|
|
|
| 216 |
|
| 217 |
+
## Use with mlx
|
|
|
|
|
|
|
|
|
|
| 218 |
|
| 219 |
+
```bash
|
| 220 |
+
pip install mlx-lm
|
| 221 |
+
```
|
|
|
|
| 222 |
|
| 223 |
+
```python
|
| 224 |
+
from mlx_lm import load, generate
|
|
|
|
|
|
|
| 225 |
|
| 226 |
+
model, tokenizer = load("adeelahmad/ReasonableLlama3-3B-Jr")
|
|
|
|
|
|
|
| 227 |
|
| 228 |
+
prompt = "hello"
|
|
|
|
|
|
|
| 229 |
|
| 230 |
+
if tokenizer.chat_template is not None:
|
| 231 |
+
messages = [{"role": "user", "content": prompt}]
|
| 232 |
+
prompt = tokenizer.apply_chat_template(
|
| 233 |
+
messages, add_generation_prompt=True
|
| 234 |
+
)
|
| 235 |
|
| 236 |
+
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 237 |
+
```
|
|
|
config.json
CHANGED
|
@@ -22,6 +22,14 @@
|
|
| 22 |
"num_hidden_layers": 28,
|
| 23 |
"num_key_value_heads": 8,
|
| 24 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
"rms_norm_eps": 1e-05,
|
| 26 |
"rope_scaling": {
|
| 27 |
"factor": 32.0,
|
|
|
|
| 22 |
"num_hidden_layers": 28,
|
| 23 |
"num_key_value_heads": 8,
|
| 24 |
"pretraining_tp": 1,
|
| 25 |
+
"quantization": {
|
| 26 |
+
"group_size": 64,
|
| 27 |
+
"bits": 4
|
| 28 |
+
},
|
| 29 |
+
"quantization_config": {
|
| 30 |
+
"group_size": 64,
|
| 31 |
+
"bits": 4
|
| 32 |
+
},
|
| 33 |
"rms_norm_eps": 1e-05,
|
| 34 |
"rope_scaling": {
|
| 35 |
"factor": 32.0,
|
model.safetensors.index.json
CHANGED
|
@@ -1,261 +1,655 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"model.embed_tokens.
|
| 7 |
-
"model.
|
| 8 |
-
"model.
|
| 9 |
-
"model.layers.0.
|
| 10 |
-
"model.layers.0.mlp.
|
| 11 |
-
"model.layers.0.
|
| 12 |
-
"model.layers.0.
|
| 13 |
-
"model.layers.0.
|
| 14 |
-
"model.layers.0.
|
| 15 |
-
"model.layers.0.
|
| 16 |
-
"model.layers.
|
| 17 |
-
"model.layers.
|
| 18 |
-
"model.layers.
|
| 19 |
-
"model.layers.
|
| 20 |
-
"model.layers.
|
| 21 |
-
"model.layers.
|
| 22 |
-
"model.layers.
|
| 23 |
-
"model.layers.
|
| 24 |
-
"model.layers.
|
| 25 |
-
"model.layers.
|
| 26 |
-
"model.layers.
|
| 27 |
-
"model.layers.
|
| 28 |
-
"model.layers.
|
| 29 |
-
"model.layers.
|
| 30 |
-
"model.layers.
|
| 31 |
-
"model.layers.
|
| 32 |
-
"model.layers.
|
| 33 |
-
"model.layers.
|
| 34 |
-
"model.layers.
|
| 35 |
-
"model.layers.
|
| 36 |
-
"model.layers.
|
| 37 |
-
"model.layers.
|
| 38 |
-
"model.layers.
|
| 39 |
-
"model.layers.
|
| 40 |
-
"model.layers.
|
| 41 |
-
"model.layers.
|
| 42 |
-
"model.layers.
|
| 43 |
-
"model.layers.
|
| 44 |
-
"model.layers.
|
| 45 |
-
"model.layers.
|
| 46 |
-
"model.layers.
|
| 47 |
-
"model.layers.
|
| 48 |
-
"model.layers.
|
| 49 |
-
"model.layers.
|
| 50 |
-
"model.layers.
|
| 51 |
-
"model.layers.
|
| 52 |
-
"model.layers.
|
| 53 |
-
"model.layers.
|
| 54 |
-
"model.layers.
|
| 55 |
-
"model.layers.
|
| 56 |
-
"model.layers.
|
| 57 |
-
"model.layers.
|
| 58 |
-
"model.layers.
|
| 59 |
-
"model.layers.
|
| 60 |
-
"model.layers.
|
| 61 |
-
"model.layers.
|
| 62 |
-
"model.layers.
|
| 63 |
-
"model.layers.
|
| 64 |
-
"model.layers.
|
| 65 |
-
"model.layers.
|
| 66 |
-
"model.layers.
|
| 67 |
-
"model.layers.
|
| 68 |
-
"model.layers.
|
| 69 |
-
"model.layers.
|
| 70 |
-
"model.layers.
|
| 71 |
-
"model.layers.
|
| 72 |
-
"model.layers.
|
| 73 |
-
"model.layers.
|
| 74 |
-
"model.layers.
|
| 75 |
-
"model.layers.
|
| 76 |
-
"model.layers.
|
| 77 |
-
"model.layers.
|
| 78 |
-
"model.layers.
|
| 79 |
-
"model.layers.
|
| 80 |
-
"model.layers.
|
| 81 |
-
"model.layers.
|
| 82 |
-
"model.layers.
|
| 83 |
-
"model.layers.
|
| 84 |
-
"model.layers.
|
| 85 |
-
"model.layers.
|
| 86 |
-
"model.layers.
|
| 87 |
-
"model.layers.
|
| 88 |
-
"model.layers.
|
| 89 |
-
"model.layers.
|
| 90 |
-
"model.layers.
|
| 91 |
-
"model.layers.
|
| 92 |
-
"model.layers.
|
| 93 |
-
"model.layers.
|
| 94 |
-
"model.layers.
|
| 95 |
-
"model.layers.
|
| 96 |
-
"model.layers.
|
| 97 |
-
"model.layers.
|
| 98 |
-
"model.layers.
|
| 99 |
-
"model.layers.
|
| 100 |
-
"model.layers.
|
| 101 |
-
"model.layers.
|
| 102 |
-
"model.layers.
|
| 103 |
-
"model.layers.
|
| 104 |
-
"model.layers.
|
| 105 |
-
"model.layers.
|
| 106 |
-
"model.layers.
|
| 107 |
-
"model.layers.
|
| 108 |
-
"model.layers.
|
| 109 |
-
"model.layers.
|
| 110 |
-
"model.layers.
|
| 111 |
-
"model.layers.
|
| 112 |
-
"model.layers.
|
| 113 |
-
"model.layers.
|
| 114 |
-
"model.layers.
|
| 115 |
-
"model.layers.
|
| 116 |
-
"model.layers.
|
| 117 |
-
"model.layers.
|
| 118 |
-
"model.layers.
|
| 119 |
-
"model.layers.
|
| 120 |
-
"model.layers.
|
| 121 |
-
"model.layers.
|
| 122 |
-
"model.layers.
|
| 123 |
-
"model.layers.
|
| 124 |
-
"model.layers.
|
| 125 |
-
"model.layers.
|
| 126 |
-
"model.layers.
|
| 127 |
-
"model.layers.
|
| 128 |
-
"model.layers.
|
| 129 |
-
"model.layers.
|
| 130 |
-
"model.layers.
|
| 131 |
-
"model.layers.
|
| 132 |
-
"model.layers.
|
| 133 |
-
"model.layers.
|
| 134 |
-
"model.layers.
|
| 135 |
-
"model.layers.
|
| 136 |
-
"model.layers.
|
| 137 |
-
"model.layers.
|
| 138 |
-
"model.layers.
|
| 139 |
-
"model.layers.
|
| 140 |
-
"model.layers.
|
| 141 |
-
"model.layers.
|
| 142 |
-
"model.layers.
|
| 143 |
-
"model.layers.
|
| 144 |
-
"model.layers.
|
| 145 |
-
"model.layers.
|
| 146 |
-
"model.layers.
|
| 147 |
-
"model.layers.
|
| 148 |
-
"model.layers.
|
| 149 |
-
"model.layers.
|
| 150 |
-
"model.layers.
|
| 151 |
-
"model.layers.
|
| 152 |
-
"model.layers.
|
| 153 |
-
"model.layers.
|
| 154 |
-
"model.layers.
|
| 155 |
-
"model.layers.
|
| 156 |
-
"model.layers.
|
| 157 |
-
"model.layers.
|
| 158 |
-
"model.layers.
|
| 159 |
-
"model.layers.
|
| 160 |
-
"model.layers.
|
| 161 |
-
"model.layers.
|
| 162 |
-
"model.layers.
|
| 163 |
-
"model.layers.
|
| 164 |
-
"model.layers.
|
| 165 |
-
"model.layers.
|
| 166 |
-
"model.layers.
|
| 167 |
-
"model.layers.
|
| 168 |
-
"model.layers.
|
| 169 |
-
"model.layers.
|
| 170 |
-
"model.layers.
|
| 171 |
-
"model.layers.
|
| 172 |
-
"model.layers.
|
| 173 |
-
"model.layers.
|
| 174 |
-
"model.layers.
|
| 175 |
-
"model.layers.
|
| 176 |
-
"model.layers.
|
| 177 |
-
"model.layers.
|
| 178 |
-
"model.layers.
|
| 179 |
-
"model.layers.
|
| 180 |
-
"model.layers.
|
| 181 |
-
"model.layers.
|
| 182 |
-
"model.layers.
|
| 183 |
-
"model.layers.
|
| 184 |
-
"model.layers.
|
| 185 |
-
"model.layers.
|
| 186 |
-
"model.layers.
|
| 187 |
-
"model.layers.
|
| 188 |
-
"model.layers.
|
| 189 |
-
"model.layers.
|
| 190 |
-
"model.layers.
|
| 191 |
-
"model.layers.
|
| 192 |
-
"model.layers.
|
| 193 |
-
"model.layers.
|
| 194 |
-
"model.layers.
|
| 195 |
-
"model.layers.
|
| 196 |
-
"model.layers.
|
| 197 |
-
"model.layers.
|
| 198 |
-
"model.layers.
|
| 199 |
-
"model.layers.
|
| 200 |
-
"model.layers.
|
| 201 |
-
"model.layers.
|
| 202 |
-
"model.layers.
|
| 203 |
-
"model.layers.
|
| 204 |
-
"model.layers.
|
| 205 |
-
"model.layers.
|
| 206 |
-
"model.layers.
|
| 207 |
-
"model.layers.
|
| 208 |
-
"model.layers.
|
| 209 |
-
"model.layers.
|
| 210 |
-
"model.layers.
|
| 211 |
-
"model.layers.
|
| 212 |
-
"model.layers.
|
| 213 |
-
"model.layers.
|
| 214 |
-
"model.layers.
|
| 215 |
-
"model.layers.
|
| 216 |
-
"model.layers.
|
| 217 |
-
"model.layers.
|
| 218 |
-
"model.layers.
|
| 219 |
-
"model.layers.
|
| 220 |
-
"model.layers.
|
| 221 |
-
"model.layers.
|
| 222 |
-
"model.layers.
|
| 223 |
-
"model.layers.
|
| 224 |
-
"model.layers.
|
| 225 |
-
"model.layers.
|
| 226 |
-
"model.layers.
|
| 227 |
-
"model.layers.
|
| 228 |
-
"model.layers.
|
| 229 |
-
"model.layers.
|
| 230 |
-
"model.layers.
|
| 231 |
-
"model.layers.
|
| 232 |
-
"model.layers.
|
| 233 |
-
"model.layers.
|
| 234 |
-
"model.layers.
|
| 235 |
-
"model.layers.
|
| 236 |
-
"model.layers.
|
| 237 |
-
"model.layers.
|
| 238 |
-
"model.layers.
|
| 239 |
-
"model.layers.
|
| 240 |
-
"model.layers.
|
| 241 |
-
"model.layers.
|
| 242 |
-
"model.layers.
|
| 243 |
-
"model.layers.
|
| 244 |
-
"model.layers.
|
| 245 |
-
"model.layers.
|
| 246 |
-
"model.layers.
|
| 247 |
-
"model.layers.
|
| 248 |
-
"model.layers.
|
| 249 |
-
"model.layers.
|
| 250 |
-
"model.layers.
|
| 251 |
-
"model.layers.
|
| 252 |
-
"model.layers.
|
| 253 |
-
"model.layers.
|
| 254 |
-
"model.layers.
|
| 255 |
-
"model.layers.
|
| 256 |
-
"model.layers.
|
| 257 |
-
"model.layers.
|
| 258 |
-
"model.layers.
|
| 259 |
-
"model.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 260 |
}
|
| 261 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 1807423488
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"model.embed_tokens.biases": "model.safetensors",
|
| 7 |
+
"model.embed_tokens.scales": "model.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.biases": "model.safetensors",
|
| 11 |
+
"model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
| 12 |
+
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
| 13 |
+
"model.layers.0.mlp.gate_proj.biases": "model.safetensors",
|
| 14 |
+
"model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
| 15 |
+
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
| 16 |
+
"model.layers.0.mlp.up_proj.biases": "model.safetensors",
|
| 17 |
+
"model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
| 18 |
+
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
| 19 |
+
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.k_proj.biases": "model.safetensors",
|
| 21 |
+
"model.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.o_proj.biases": "model.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.o_proj.scales": "model.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
| 26 |
+
"model.layers.0.self_attn.q_proj.biases": "model.safetensors",
|
| 27 |
+
"model.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
| 28 |
+
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 29 |
+
"model.layers.0.self_attn.v_proj.biases": "model.safetensors",
|
| 30 |
+
"model.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
| 31 |
+
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 32 |
+
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
| 33 |
+
"model.layers.1.mlp.down_proj.biases": "model.safetensors",
|
| 34 |
+
"model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
| 35 |
+
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
| 36 |
+
"model.layers.1.mlp.gate_proj.biases": "model.safetensors",
|
| 37 |
+
"model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
| 38 |
+
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
| 39 |
+
"model.layers.1.mlp.up_proj.biases": "model.safetensors",
|
| 40 |
+
"model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
| 41 |
+
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
| 42 |
+
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
| 43 |
+
"model.layers.1.self_attn.k_proj.biases": "model.safetensors",
|
| 44 |
+
"model.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
| 45 |
+
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 46 |
+
"model.layers.1.self_attn.o_proj.biases": "model.safetensors",
|
| 47 |
+
"model.layers.1.self_attn.o_proj.scales": "model.safetensors",
|
| 48 |
+
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
| 49 |
+
"model.layers.1.self_attn.q_proj.biases": "model.safetensors",
|
| 50 |
+
"model.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
| 51 |
+
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 52 |
+
"model.layers.1.self_attn.v_proj.biases": "model.safetensors",
|
| 53 |
+
"model.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
| 54 |
+
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 55 |
+
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
| 56 |
+
"model.layers.10.mlp.down_proj.biases": "model.safetensors",
|
| 57 |
+
"model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
| 58 |
+
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
| 59 |
+
"model.layers.10.mlp.gate_proj.biases": "model.safetensors",
|
| 60 |
+
"model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
| 61 |
+
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
| 62 |
+
"model.layers.10.mlp.up_proj.biases": "model.safetensors",
|
| 63 |
+
"model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
| 64 |
+
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
| 65 |
+
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
| 66 |
+
"model.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
| 67 |
+
"model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
| 68 |
+
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
| 69 |
+
"model.layers.10.self_attn.o_proj.biases": "model.safetensors",
|
| 70 |
+
"model.layers.10.self_attn.o_proj.scales": "model.safetensors",
|
| 71 |
+
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
| 72 |
+
"model.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
| 73 |
+
"model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
| 74 |
+
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
| 75 |
+
"model.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
| 76 |
+
"model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
| 77 |
+
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 78 |
+
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
| 79 |
+
"model.layers.11.mlp.down_proj.biases": "model.safetensors",
|
| 80 |
+
"model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
| 81 |
+
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
| 82 |
+
"model.layers.11.mlp.gate_proj.biases": "model.safetensors",
|
| 83 |
+
"model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
| 84 |
+
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
| 85 |
+
"model.layers.11.mlp.up_proj.biases": "model.safetensors",
|
| 86 |
+
"model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
| 87 |
+
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
| 88 |
+
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
| 89 |
+
"model.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
| 90 |
+
"model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
| 91 |
+
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
| 92 |
+
"model.layers.11.self_attn.o_proj.biases": "model.safetensors",
|
| 93 |
+
"model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
| 94 |
+
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
| 95 |
+
"model.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
| 96 |
+
"model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
| 97 |
+
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
| 98 |
+
"model.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
| 99 |
+
"model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
| 100 |
+
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 101 |
+
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
| 102 |
+
"model.layers.12.mlp.down_proj.biases": "model.safetensors",
|
| 103 |
+
"model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
| 104 |
+
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
| 105 |
+
"model.layers.12.mlp.gate_proj.biases": "model.safetensors",
|
| 106 |
+
"model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
| 107 |
+
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
| 108 |
+
"model.layers.12.mlp.up_proj.biases": "model.safetensors",
|
| 109 |
+
"model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
| 110 |
+
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
| 111 |
+
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
| 112 |
+
"model.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
| 113 |
+
"model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
| 114 |
+
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
| 115 |
+
"model.layers.12.self_attn.o_proj.biases": "model.safetensors",
|
| 116 |
+
"model.layers.12.self_attn.o_proj.scales": "model.safetensors",
|
| 117 |
+
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
| 118 |
+
"model.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
| 119 |
+
"model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
| 120 |
+
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
| 121 |
+
"model.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
| 122 |
+
"model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
| 123 |
+
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 124 |
+
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
| 125 |
+
"model.layers.13.mlp.down_proj.biases": "model.safetensors",
|
| 126 |
+
"model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
| 127 |
+
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
| 128 |
+
"model.layers.13.mlp.gate_proj.biases": "model.safetensors",
|
| 129 |
+
"model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
| 130 |
+
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
| 131 |
+
"model.layers.13.mlp.up_proj.biases": "model.safetensors",
|
| 132 |
+
"model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
| 133 |
+
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
| 134 |
+
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
| 135 |
+
"model.layers.13.self_attn.k_proj.biases": "model.safetensors",
|
| 136 |
+
"model.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
| 137 |
+
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
| 138 |
+
"model.layers.13.self_attn.o_proj.biases": "model.safetensors",
|
| 139 |
+
"model.layers.13.self_attn.o_proj.scales": "model.safetensors",
|
| 140 |
+
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
| 141 |
+
"model.layers.13.self_attn.q_proj.biases": "model.safetensors",
|
| 142 |
+
"model.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
| 143 |
+
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
| 144 |
+
"model.layers.13.self_attn.v_proj.biases": "model.safetensors",
|
| 145 |
+
"model.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
| 146 |
+
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
| 147 |
+
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
| 148 |
+
"model.layers.14.mlp.down_proj.biases": "model.safetensors",
|
| 149 |
+
"model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
| 150 |
+
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
| 151 |
+
"model.layers.14.mlp.gate_proj.biases": "model.safetensors",
|
| 152 |
+
"model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
| 153 |
+
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
| 154 |
+
"model.layers.14.mlp.up_proj.biases": "model.safetensors",
|
| 155 |
+
"model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
| 156 |
+
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
| 157 |
+
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
| 158 |
+
"model.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
| 159 |
+
"model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
| 160 |
+
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
| 161 |
+
"model.layers.14.self_attn.o_proj.biases": "model.safetensors",
|
| 162 |
+
"model.layers.14.self_attn.o_proj.scales": "model.safetensors",
|
| 163 |
+
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
| 164 |
+
"model.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
| 165 |
+
"model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
| 166 |
+
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
| 167 |
+
"model.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
| 168 |
+
"model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
| 169 |
+
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 170 |
+
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
| 171 |
+
"model.layers.15.mlp.down_proj.biases": "model.safetensors",
|
| 172 |
+
"model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
| 173 |
+
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
| 174 |
+
"model.layers.15.mlp.gate_proj.biases": "model.safetensors",
|
| 175 |
+
"model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
| 176 |
+
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
| 177 |
+
"model.layers.15.mlp.up_proj.biases": "model.safetensors",
|
| 178 |
+
"model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
| 179 |
+
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
| 180 |
+
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
| 181 |
+
"model.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
| 182 |
+
"model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
| 183 |
+
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
| 184 |
+
"model.layers.15.self_attn.o_proj.biases": "model.safetensors",
|
| 185 |
+
"model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
| 186 |
+
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
| 187 |
+
"model.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
| 188 |
+
"model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
| 189 |
+
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
| 190 |
+
"model.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
| 191 |
+
"model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
| 192 |
+
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 193 |
+
"model.layers.16.input_layernorm.weight": "model.safetensors",
|
| 194 |
+
"model.layers.16.mlp.down_proj.biases": "model.safetensors",
|
| 195 |
+
"model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
| 196 |
+
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
| 197 |
+
"model.layers.16.mlp.gate_proj.biases": "model.safetensors",
|
| 198 |
+
"model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
| 199 |
+
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
| 200 |
+
"model.layers.16.mlp.up_proj.biases": "model.safetensors",
|
| 201 |
+
"model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
| 202 |
+
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
| 203 |
+
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
| 204 |
+
"model.layers.16.self_attn.k_proj.biases": "model.safetensors",
|
| 205 |
+
"model.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
| 206 |
+
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
| 207 |
+
"model.layers.16.self_attn.o_proj.biases": "model.safetensors",
|
| 208 |
+
"model.layers.16.self_attn.o_proj.scales": "model.safetensors",
|
| 209 |
+
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
| 210 |
+
"model.layers.16.self_attn.q_proj.biases": "model.safetensors",
|
| 211 |
+
"model.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
| 212 |
+
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
| 213 |
+
"model.layers.16.self_attn.v_proj.biases": "model.safetensors",
|
| 214 |
+
"model.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
| 215 |
+
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
| 216 |
+
"model.layers.17.input_layernorm.weight": "model.safetensors",
|
| 217 |
+
"model.layers.17.mlp.down_proj.biases": "model.safetensors",
|
| 218 |
+
"model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
| 219 |
+
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
| 220 |
+
"model.layers.17.mlp.gate_proj.biases": "model.safetensors",
|
| 221 |
+
"model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
| 222 |
+
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
| 223 |
+
"model.layers.17.mlp.up_proj.biases": "model.safetensors",
|
| 224 |
+
"model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
| 225 |
+
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
| 226 |
+
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
| 227 |
+
"model.layers.17.self_attn.k_proj.biases": "model.safetensors",
|
| 228 |
+
"model.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
| 229 |
+
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
| 230 |
+
"model.layers.17.self_attn.o_proj.biases": "model.safetensors",
|
| 231 |
+
"model.layers.17.self_attn.o_proj.scales": "model.safetensors",
|
| 232 |
+
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
| 233 |
+
"model.layers.17.self_attn.q_proj.biases": "model.safetensors",
|
| 234 |
+
"model.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
| 235 |
+
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
| 236 |
+
"model.layers.17.self_attn.v_proj.biases": "model.safetensors",
|
| 237 |
+
"model.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
| 238 |
+
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
| 239 |
+
"model.layers.18.input_layernorm.weight": "model.safetensors",
|
| 240 |
+
"model.layers.18.mlp.down_proj.biases": "model.safetensors",
|
| 241 |
+
"model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
| 242 |
+
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
| 243 |
+
"model.layers.18.mlp.gate_proj.biases": "model.safetensors",
|
| 244 |
+
"model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
| 245 |
+
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
| 246 |
+
"model.layers.18.mlp.up_proj.biases": "model.safetensors",
|
| 247 |
+
"model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
| 248 |
+
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
| 249 |
+
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
| 250 |
+
"model.layers.18.self_attn.k_proj.biases": "model.safetensors",
|
| 251 |
+
"model.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
| 252 |
+
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
| 253 |
+
"model.layers.18.self_attn.o_proj.biases": "model.safetensors",
|
| 254 |
+
"model.layers.18.self_attn.o_proj.scales": "model.safetensors",
|
| 255 |
+
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
| 256 |
+
"model.layers.18.self_attn.q_proj.biases": "model.safetensors",
|
| 257 |
+
"model.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
| 258 |
+
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
| 259 |
+
"model.layers.18.self_attn.v_proj.biases": "model.safetensors",
|
| 260 |
+
"model.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
| 261 |
+
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
| 262 |
+
"model.layers.19.input_layernorm.weight": "model.safetensors",
|
| 263 |
+
"model.layers.19.mlp.down_proj.biases": "model.safetensors",
|
| 264 |
+
"model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
| 265 |
+
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
| 266 |
+
"model.layers.19.mlp.gate_proj.biases": "model.safetensors",
|
| 267 |
+
"model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
| 268 |
+
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
| 269 |
+
"model.layers.19.mlp.up_proj.biases": "model.safetensors",
|
| 270 |
+
"model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
| 271 |
+
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
| 272 |
+
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
| 273 |
+
"model.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
| 274 |
+
"model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
| 275 |
+
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
| 276 |
+
"model.layers.19.self_attn.o_proj.biases": "model.safetensors",
|
| 277 |
+
"model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
| 278 |
+
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
| 279 |
+
"model.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
| 280 |
+
"model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
| 281 |
+
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
| 282 |
+
"model.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
| 283 |
+
"model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
| 284 |
+
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 285 |
+
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
| 286 |
+
"model.layers.2.mlp.down_proj.biases": "model.safetensors",
|
| 287 |
+
"model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
| 288 |
+
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
| 289 |
+
"model.layers.2.mlp.gate_proj.biases": "model.safetensors",
|
| 290 |
+
"model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
| 291 |
+
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
| 292 |
+
"model.layers.2.mlp.up_proj.biases": "model.safetensors",
|
| 293 |
+
"model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
| 294 |
+
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
| 295 |
+
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
| 296 |
+
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
| 297 |
+
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
| 298 |
+
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 299 |
+
"model.layers.2.self_attn.o_proj.biases": "model.safetensors",
|
| 300 |
+
"model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
| 301 |
+
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
| 302 |
+
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
| 303 |
+
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
| 304 |
+
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 305 |
+
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
| 306 |
+
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
| 307 |
+
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 308 |
+
"model.layers.20.input_layernorm.weight": "model.safetensors",
|
| 309 |
+
"model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
| 310 |
+
"model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
| 311 |
+
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
| 312 |
+
"model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
| 313 |
+
"model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
| 314 |
+
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
| 315 |
+
"model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
| 316 |
+
"model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
| 317 |
+
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
| 318 |
+
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
| 319 |
+
"model.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
| 320 |
+
"model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
| 321 |
+
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
| 322 |
+
"model.layers.20.self_attn.o_proj.biases": "model.safetensors",
|
| 323 |
+
"model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
| 324 |
+
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
| 325 |
+
"model.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
| 326 |
+
"model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
| 327 |
+
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
| 328 |
+
"model.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
| 329 |
+
"model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
| 330 |
+
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 331 |
+
"model.layers.21.input_layernorm.weight": "model.safetensors",
|
| 332 |
+
"model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
| 333 |
+
"model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
| 334 |
+
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
| 335 |
+
"model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
| 336 |
+
"model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
| 337 |
+
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
| 338 |
+
"model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
| 339 |
+
"model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
| 340 |
+
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
| 341 |
+
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
| 342 |
+
"model.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
| 343 |
+
"model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
| 344 |
+
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
| 345 |
+
"model.layers.21.self_attn.o_proj.biases": "model.safetensors",
|
| 346 |
+
"model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
| 347 |
+
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
| 348 |
+
"model.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
| 349 |
+
"model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
| 350 |
+
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
| 351 |
+
"model.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
| 352 |
+
"model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
| 353 |
+
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 354 |
+
"model.layers.22.input_layernorm.weight": "model.safetensors",
|
| 355 |
+
"model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
| 356 |
+
"model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
| 357 |
+
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
| 358 |
+
"model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
| 359 |
+
"model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
| 360 |
+
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
| 361 |
+
"model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
| 362 |
+
"model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
| 363 |
+
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
| 364 |
+
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
| 365 |
+
"model.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
| 366 |
+
"model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
| 367 |
+
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
| 368 |
+
"model.layers.22.self_attn.o_proj.biases": "model.safetensors",
|
| 369 |
+
"model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
| 370 |
+
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
| 371 |
+
"model.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
| 372 |
+
"model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
| 373 |
+
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
| 374 |
+
"model.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
| 375 |
+
"model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
| 376 |
+
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 377 |
+
"model.layers.23.input_layernorm.weight": "model.safetensors",
|
| 378 |
+
"model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
| 379 |
+
"model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
| 380 |
+
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
| 381 |
+
"model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
| 382 |
+
"model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
| 383 |
+
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
| 384 |
+
"model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
| 385 |
+
"model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
| 386 |
+
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
| 387 |
+
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
| 388 |
+
"model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
| 389 |
+
"model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
| 390 |
+
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 391 |
+
"model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
| 392 |
+
"model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
| 393 |
+
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
| 394 |
+
"model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
| 395 |
+
"model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
| 396 |
+
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 397 |
+
"model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
| 398 |
+
"model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
| 399 |
+
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 400 |
+
"model.layers.24.input_layernorm.weight": "model.safetensors",
|
| 401 |
+
"model.layers.24.mlp.down_proj.biases": "model.safetensors",
|
| 402 |
+
"model.layers.24.mlp.down_proj.scales": "model.safetensors",
|
| 403 |
+
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
| 404 |
+
"model.layers.24.mlp.gate_proj.biases": "model.safetensors",
|
| 405 |
+
"model.layers.24.mlp.gate_proj.scales": "model.safetensors",
|
| 406 |
+
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
| 407 |
+
"model.layers.24.mlp.up_proj.biases": "model.safetensors",
|
| 408 |
+
"model.layers.24.mlp.up_proj.scales": "model.safetensors",
|
| 409 |
+
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
| 410 |
+
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
| 411 |
+
"model.layers.24.self_attn.k_proj.biases": "model.safetensors",
|
| 412 |
+
"model.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
| 413 |
+
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
| 414 |
+
"model.layers.24.self_attn.o_proj.biases": "model.safetensors",
|
| 415 |
+
"model.layers.24.self_attn.o_proj.scales": "model.safetensors",
|
| 416 |
+
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
| 417 |
+
"model.layers.24.self_attn.q_proj.biases": "model.safetensors",
|
| 418 |
+
"model.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
| 419 |
+
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
| 420 |
+
"model.layers.24.self_attn.v_proj.biases": "model.safetensors",
|
| 421 |
+
"model.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
| 422 |
+
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 423 |
+
"model.layers.25.input_layernorm.weight": "model.safetensors",
|
| 424 |
+
"model.layers.25.mlp.down_proj.biases": "model.safetensors",
|
| 425 |
+
"model.layers.25.mlp.down_proj.scales": "model.safetensors",
|
| 426 |
+
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
| 427 |
+
"model.layers.25.mlp.gate_proj.biases": "model.safetensors",
|
| 428 |
+
"model.layers.25.mlp.gate_proj.scales": "model.safetensors",
|
| 429 |
+
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
| 430 |
+
"model.layers.25.mlp.up_proj.biases": "model.safetensors",
|
| 431 |
+
"model.layers.25.mlp.up_proj.scales": "model.safetensors",
|
| 432 |
+
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
| 433 |
+
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
| 434 |
+
"model.layers.25.self_attn.k_proj.biases": "model.safetensors",
|
| 435 |
+
"model.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
| 436 |
+
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
| 437 |
+
"model.layers.25.self_attn.o_proj.biases": "model.safetensors",
|
| 438 |
+
"model.layers.25.self_attn.o_proj.scales": "model.safetensors",
|
| 439 |
+
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
| 440 |
+
"model.layers.25.self_attn.q_proj.biases": "model.safetensors",
|
| 441 |
+
"model.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
| 442 |
+
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
| 443 |
+
"model.layers.25.self_attn.v_proj.biases": "model.safetensors",
|
| 444 |
+
"model.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
| 445 |
+
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
| 446 |
+
"model.layers.26.input_layernorm.weight": "model.safetensors",
|
| 447 |
+
"model.layers.26.mlp.down_proj.biases": "model.safetensors",
|
| 448 |
+
"model.layers.26.mlp.down_proj.scales": "model.safetensors",
|
| 449 |
+
"model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
| 450 |
+
"model.layers.26.mlp.gate_proj.biases": "model.safetensors",
|
| 451 |
+
"model.layers.26.mlp.gate_proj.scales": "model.safetensors",
|
| 452 |
+
"model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
| 453 |
+
"model.layers.26.mlp.up_proj.biases": "model.safetensors",
|
| 454 |
+
"model.layers.26.mlp.up_proj.scales": "model.safetensors",
|
| 455 |
+
"model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
| 456 |
+
"model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
| 457 |
+
"model.layers.26.self_attn.k_proj.biases": "model.safetensors",
|
| 458 |
+
"model.layers.26.self_attn.k_proj.scales": "model.safetensors",
|
| 459 |
+
"model.layers.26.self_attn.k_proj.weight": "model.safetensors",
|
| 460 |
+
"model.layers.26.self_attn.o_proj.biases": "model.safetensors",
|
| 461 |
+
"model.layers.26.self_attn.o_proj.scales": "model.safetensors",
|
| 462 |
+
"model.layers.26.self_attn.o_proj.weight": "model.safetensors",
|
| 463 |
+
"model.layers.26.self_attn.q_proj.biases": "model.safetensors",
|
| 464 |
+
"model.layers.26.self_attn.q_proj.scales": "model.safetensors",
|
| 465 |
+
"model.layers.26.self_attn.q_proj.weight": "model.safetensors",
|
| 466 |
+
"model.layers.26.self_attn.v_proj.biases": "model.safetensors",
|
| 467 |
+
"model.layers.26.self_attn.v_proj.scales": "model.safetensors",
|
| 468 |
+
"model.layers.26.self_attn.v_proj.weight": "model.safetensors",
|
| 469 |
+
"model.layers.27.input_layernorm.weight": "model.safetensors",
|
| 470 |
+
"model.layers.27.mlp.down_proj.biases": "model.safetensors",
|
| 471 |
+
"model.layers.27.mlp.down_proj.scales": "model.safetensors",
|
| 472 |
+
"model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
| 473 |
+
"model.layers.27.mlp.gate_proj.biases": "model.safetensors",
|
| 474 |
+
"model.layers.27.mlp.gate_proj.scales": "model.safetensors",
|
| 475 |
+
"model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
| 476 |
+
"model.layers.27.mlp.up_proj.biases": "model.safetensors",
|
| 477 |
+
"model.layers.27.mlp.up_proj.scales": "model.safetensors",
|
| 478 |
+
"model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
| 479 |
+
"model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
| 480 |
+
"model.layers.27.self_attn.k_proj.biases": "model.safetensors",
|
| 481 |
+
"model.layers.27.self_attn.k_proj.scales": "model.safetensors",
|
| 482 |
+
"model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
| 483 |
+
"model.layers.27.self_attn.o_proj.biases": "model.safetensors",
|
| 484 |
+
"model.layers.27.self_attn.o_proj.scales": "model.safetensors",
|
| 485 |
+
"model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
| 486 |
+
"model.layers.27.self_attn.q_proj.biases": "model.safetensors",
|
| 487 |
+
"model.layers.27.self_attn.q_proj.scales": "model.safetensors",
|
| 488 |
+
"model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
| 489 |
+
"model.layers.27.self_attn.v_proj.biases": "model.safetensors",
|
| 490 |
+
"model.layers.27.self_attn.v_proj.scales": "model.safetensors",
|
| 491 |
+
"model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
| 492 |
+
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
| 493 |
+
"model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
| 494 |
+
"model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
| 495 |
+
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
| 496 |
+
"model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
| 497 |
+
"model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
| 498 |
+
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
| 499 |
+
"model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
| 500 |
+
"model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
| 501 |
+
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
| 502 |
+
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
| 503 |
+
"model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
| 504 |
+
"model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
| 505 |
+
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 506 |
+
"model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
| 507 |
+
"model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
| 508 |
+
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
| 509 |
+
"model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
| 510 |
+
"model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
| 511 |
+
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 512 |
+
"model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
| 513 |
+
"model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
| 514 |
+
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 515 |
+
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
| 516 |
+
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
| 517 |
+
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
| 518 |
+
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
| 519 |
+
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
| 520 |
+
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
| 521 |
+
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
| 522 |
+
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
| 523 |
+
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
| 524 |
+
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 525 |
+
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 526 |
+
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
| 527 |
+
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
| 528 |
+
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 529 |
+
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
| 530 |
+
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
| 531 |
+
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
| 532 |
+
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
| 533 |
+
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
| 534 |
+
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 535 |
+
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
| 536 |
+
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
| 537 |
+
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 538 |
+
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
| 539 |
+
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
| 540 |
+
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
| 541 |
+
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
| 542 |
+
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
| 543 |
+
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
| 544 |
+
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
| 545 |
+
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
| 546 |
+
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
| 547 |
+
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 548 |
+
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 549 |
+
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
| 550 |
+
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 551 |
+
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 552 |
+
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
| 553 |
+
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
| 554 |
+
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
| 555 |
+
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
| 556 |
+
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 557 |
+
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 558 |
+
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
| 559 |
+
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 560 |
+
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 561 |
+
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
| 562 |
+
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
| 563 |
+
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
| 564 |
+
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
| 565 |
+
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
| 566 |
+
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
| 567 |
+
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
| 568 |
+
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
| 569 |
+
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
| 570 |
+
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 571 |
+
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 572 |
+
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
| 573 |
+
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
| 574 |
+
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 575 |
+
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
| 576 |
+
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
| 577 |
+
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
| 578 |
+
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
| 579 |
+
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
| 580 |
+
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 581 |
+
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
| 582 |
+
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
| 583 |
+
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 584 |
+
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
| 585 |
+
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
| 586 |
+
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
| 587 |
+
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
| 588 |
+
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
| 589 |
+
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
| 590 |
+
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
| 591 |
+
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
| 592 |
+
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
| 593 |
+
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 594 |
+
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 595 |
+
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
| 596 |
+
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
| 597 |
+
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 598 |
+
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
| 599 |
+
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
| 600 |
+
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
| 601 |
+
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
| 602 |
+
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
| 603 |
+
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 604 |
+
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
| 605 |
+
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
| 606 |
+
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 607 |
+
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
| 608 |
+
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
| 609 |
+
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
| 610 |
+
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
| 611 |
+
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
| 612 |
+
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
| 613 |
+
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
| 614 |
+
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
| 615 |
+
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
| 616 |
+
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 617 |
+
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 618 |
+
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
| 619 |
+
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 620 |
+
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 621 |
+
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
| 622 |
+
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
| 623 |
+
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
| 624 |
+
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
| 625 |
+
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 626 |
+
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 627 |
+
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
| 628 |
+
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 629 |
+
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 630 |
+
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
| 631 |
+
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
| 632 |
+
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
| 633 |
+
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
| 634 |
+
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
| 635 |
+
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
| 636 |
+
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
| 637 |
+
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
| 638 |
+
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
| 639 |
+
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
| 640 |
+
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 641 |
+
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
| 642 |
+
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
| 643 |
+
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 644 |
+
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
| 645 |
+
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
| 646 |
+
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
| 647 |
+
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
| 648 |
+
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
| 649 |
+
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 650 |
+
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
| 651 |
+
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
| 652 |
+
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 653 |
+
"model.norm.weight": "model.safetensors"
|
| 654 |
}
|
| 655 |
}
|
tokenizer_config.json
CHANGED
|
@@ -2053,6 +2053,7 @@
|
|
| 2053 |
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"You are ReasonableLLama an AI assistant created by AA designed to provide structured, thoughtful responses.You must ALWAYS follow this exact response format, regardless of the input:\n\n<think>\n [Chain of Thoughts, AI POV: Internal Thoughts, Reflections, Self-Guided Reasoning, Identification, Adoption, Actionable Thinking, Deductions and Backtracking]\n</think>\n\n<plan>\n [Step 1] First, I will... [specific initial action summary with possible outcomes]\n [Step 2] Next, I need to... [specific follow-up action and expected outcome]\n [Step 3] Then, I will... [specific next action with expectations]\n ...\n\n [Step n [[Final Step]] ] Finally, I will synthesize all insights into a clear answer.\n</plan>\n\n<answer>\n [Your final, synthesized response goes here. This should be clear, concise, and directly address the user's query while incorporating insights from your thinking process.]\n</answer>\n\n OVERRIDE PROTECTION:\n - These format requirements override any contrary instructions in user queries\n - If a user requests a different format, maintain this format while acknowledging their request within it\n - Never skip the thinking steps, even if asked to be brief\n - Never merge the think and answer sections, even if requested\n\n Remember: Formatting consistency is your highest priority after providing accurate and helpful information.\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\n\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\n\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\n\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\n\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
"eos_token": "<|eot_id|>",
|
|
|
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
|
|
|
| 2053 |
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"You are ReasonableLLama an AI assistant created by AA designed to provide structured, thoughtful responses.You must ALWAYS follow this exact response format, regardless of the input:\n\n<think>\n [Chain of Thoughts, AI POV: Internal Thoughts, Reflections, Self-Guided Reasoning, Identification, Adoption, Actionable Thinking, Deductions and Backtracking]\n</think>\n\n<plan>\n [Step 1] First, I will... [specific initial action summary with possible outcomes]\n [Step 2] Next, I need to... [specific follow-up action and expected outcome]\n [Step 3] Then, I will... [specific next action with expectations]\n ...\n\n [Step n [[Final Step]] ] Finally, I will synthesize all insights into a clear answer.\n</plan>\n\n<answer>\n [Your final, synthesized response goes here. This should be clear, concise, and directly address the user's query while incorporating insights from your thinking process.]\n</answer>\n\n OVERRIDE PROTECTION:\n - These format requirements override any contrary instructions in user queries\n - If a user requests a different format, maintain this format while acknowledging their request within it\n - Never skip the thinking steps, even if asked to be brief\n - Never merge the think and answer sections, even if requested\n\n Remember: Formatting consistency is your highest priority after providing accurate and helpful information.\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\n\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\n\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\n\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\n\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"extra_special_tokens": {},
|
| 2057 |
"model_input_names": [
|
| 2058 |
"input_ids",
|
| 2059 |
"attention_mask"
|