Upload folder using huggingface_hub (#1)
Browse files- 6246123910e4f97628154d4d49bdf3a66b481d6bb907242015e791404be10397 (85ff0cade0dab75a2135776cf8d359438b92a480)
- d9d6cbb2c020d23565ae039f832a32273a0ab8646f5b33b09e716ebc9a3e0709 (ce1715447e8b29bc97847e796eeb2a6cda7388ac)
- README.md +186 -0
- config.json +29 -0
- model.safetensors +3 -0
- model.safetensors.index.json +750 -0
- special_tokens_map.json +29 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +84 -0
README.md
ADDED
|
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- code
|
| 4 |
+
license: llama2
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
tags:
|
| 7 |
+
- facebook
|
| 8 |
+
- meta
|
| 9 |
+
- pytorch
|
| 10 |
+
- llama
|
| 11 |
+
- llama-2
|
| 12 |
+
- mlx
|
| 13 |
+
extra_gated_heading: You need to share contact information with Meta to access this
|
| 14 |
+
model
|
| 15 |
+
extra_gated_prompt: "### LLAMA 2 COMMUNITY LICENSE AGREEMENT\n\"Agreement\" means\
|
| 16 |
+
\ the terms and conditions for use, reproduction, distribution and modification\
|
| 17 |
+
\ of the Llama Materials set forth herein. \"Documentation\" means the specifications,\
|
| 18 |
+
\ manuals and documentation accompanying Llama 2 distributed by Meta at https://ai.meta.com/resources/models-and-libraries/llama-downloads/.\
|
| 19 |
+
\ \"Licensee\" or \"you\" means you, or your employer or any other person or entity\
|
| 20 |
+
\ (if you are entering into this Agreement on such person or entity's behalf), of\
|
| 21 |
+
\ the age required under applicable laws, rules or regulations to provide legal\
|
| 22 |
+
\ consent and that has legal authority to bind your employer or such other person\
|
| 23 |
+
\ or entity if you are entering in this Agreement on their behalf. \"Llama 2\"\
|
| 24 |
+
\ means the foundational large language models and software and algorithms, including\
|
| 25 |
+
\ machine-learning model code, trained model weights, inference-enabling code, training-enabling\
|
| 26 |
+
\ code, fine-tuning enabling code and other elements of the foregoing distributed\
|
| 27 |
+
\ by Meta at ai.meta.com/resources/models-and-libraries/llama-downloads/. \"Llama\
|
| 28 |
+
\ Materials\" means, collectively, Meta's proprietary Llama 2 and documentation\
|
| 29 |
+
\ (and any portion thereof) made available under this Agreement. \"Meta\" or \"\
|
| 30 |
+
we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\
|
| 31 |
+
\ an entity, your principal place of business is in the EEA or Switzerland) and\
|
| 32 |
+
\ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). \
|
| 33 |
+
\ By clicking \"I Accept\" below or by using or distributing any portion or element\
|
| 34 |
+
\ of the Llama Materials, you agree to be bound by this Agreement. 1. License Rights\
|
| 35 |
+
\ and Redistribution. a. Grant of Rights. You are granted a non-exclusive, worldwide,\
|
| 36 |
+
\ non- transferable and royalty-free limited license under Meta's intellectual property\
|
| 37 |
+
\ or other rights owned by Meta embodied in the Llama Materials to use, reproduce,\
|
| 38 |
+
\ distribute, copy, create derivative works of, and make modifications to the Llama\
|
| 39 |
+
\ Materials. \n \nb. Redistribution and Use. i. If you distribute or make\
|
| 40 |
+
\ the Llama Materials, or any derivative works thereof, available to a third party,\
|
| 41 |
+
\ you shall provide a copy of this Agreement to such third party. ii. If you\
|
| 42 |
+
\ receive Llama Materials, or any derivative works thereof, from a Licensee as\
|
| 43 |
+
\ part of an integrated end user product, then Section 2 of this Agreement will\
|
| 44 |
+
\ not apply to you. iii. You must retain in all copies of the Llama Materials that\
|
| 45 |
+
\ you distribute the following attribution notice within a \"Notice\" text file\
|
| 46 |
+
\ distributed as a part of such copies: \"Llama 2 is licensed under the LLAMA 2\
|
| 47 |
+
\ Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.\"\
|
| 48 |
+
\ iv. Your use of the Llama Materials must comply with applicable laws and regulations\
|
| 49 |
+
\ (including trade compliance laws and regulations) and adhere to the Acceptable\
|
| 50 |
+
\ Use Policy for the Llama Materials (available at https://ai.meta.com/llama/use-policy),\
|
| 51 |
+
\ which is hereby incorporated by reference into this Agreement. v. You will not\
|
| 52 |
+
\ use the Llama Materials or any output or results of the Llama Materials to improve\
|
| 53 |
+
\ any other large language model (excluding Llama 2 or derivative works thereof).\
|
| 54 |
+
\ 2. Additional Commercial Terms. If, on the Llama 2 version release date, the\
|
| 55 |
+
\ monthly active users of the products or services made available by or for Licensee,\
|
| 56 |
+
\ or Licensee's affiliates, is greater than 700 million monthly active users in\
|
| 57 |
+
\ the preceding calendar month, you must request a license from Meta, which Meta\
|
| 58 |
+
\ may grant to you in its sole discretion, and you are not authorized to exercise\
|
| 59 |
+
\ any of the rights under this Agreement unless or until Meta otherwise expressly\
|
| 60 |
+
\ grants you such rights. 3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE\
|
| 61 |
+
\ LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON\
|
| 62 |
+
\ AN \"AS IS\" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED,\
|
| 63 |
+
\ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\
|
| 64 |
+
\ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\
|
| 65 |
+
\ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\
|
| 66 |
+
\ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND\
|
| 67 |
+
\ RESULTS. 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE\
|
| 68 |
+
\ LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE,\
|
| 69 |
+
\ PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST\
|
| 70 |
+
\ PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE\
|
| 71 |
+
\ DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY\
|
| 72 |
+
\ OF ANY OF THE FOREGOING. 5. Intellectual Property. a. No trademark licenses are\
|
| 73 |
+
\ granted under this Agreement, and in connection with the Llama Materials, neither\
|
| 74 |
+
\ Meta nor Licensee may use any name or mark owned by or associated with the other\
|
| 75 |
+
\ or any of its affiliates, except as required for reasonable and customary use\
|
| 76 |
+
\ in describing and redistributing the Llama Materials. b. Subject to Meta's ownership\
|
| 77 |
+
\ of Llama Materials and derivatives made by or for Meta, with respect to any derivative\
|
| 78 |
+
\ works and modifications of the Llama Materials that are made by you, as between\
|
| 79 |
+
\ you and Meta, you are and will be the owner of such derivative works and modifications.\
|
| 80 |
+
\ c. If you institute litigation or other proceedings against Meta or any entity\
|
| 81 |
+
\ (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama\
|
| 82 |
+
\ Materials or Llama 2 outputs or results, or any portion of any of the foregoing,\
|
| 83 |
+
\ constitutes infringement of intellectual property or other rights owned or licensable\
|
| 84 |
+
\ by you, then any licenses granted to you under this Agreement shall terminate\
|
| 85 |
+
\ as of the date such litigation or claim is filed or instituted. You will indemnify\
|
| 86 |
+
\ and hold harmless Meta from and against any claim by any third party arising\
|
| 87 |
+
\ out of or related to your use or distribution of the Llama Materials. 6. Term\
|
| 88 |
+
\ and Termination. The term of this Agreement will commence upon your acceptance\
|
| 89 |
+
\ of this Agreement or access to the Llama Materials and will continue in full\
|
| 90 |
+
\ force and effect until terminated in accordance with the terms and conditions\
|
| 91 |
+
\ herein. Meta may terminate this Agreement if you are in breach of any term or\
|
| 92 |
+
\ condition of this Agreement. Upon termination of this Agreement, you shall delete\
|
| 93 |
+
\ and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the \
|
| 94 |
+
\ termination of this Agreement. 7. Governing Law and Jurisdiction. This Agreement\
|
| 95 |
+
\ will be governed and construed under the laws of the State of California without\
|
| 96 |
+
\ regard to choice of law principles, and the UN Convention on Contracts for the\
|
| 97 |
+
\ International Sale of Goods does not apply to this Agreement. The courts of California\
|
| 98 |
+
\ shall have exclusive jurisdiction of any dispute arising out of this Agreement.\
|
| 99 |
+
\ USE POLICY ### Llama 2 Acceptable Use Policy Meta is committed to promoting safe\
|
| 100 |
+
\ and fair use of its tools and features, including Llama 2. If you access or use\
|
| 101 |
+
\ Llama 2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy\
|
| 102 |
+
\ of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy).\
|
| 103 |
+
\ #### Prohibited Uses We want everyone to use Llama 2 safely and responsibly. You\
|
| 104 |
+
\ agree you will not use, or allow others to use, Llama 2 to: 1. Violate the law\
|
| 105 |
+
\ or others’ rights, including to:\n 1. Engage in, promote, generate, contribute\
|
| 106 |
+
\ to, encourage, plan, incite, or further illegal or unlawful activity or content,\
|
| 107 |
+
\ such as: \n 1. Violence or terrorism \n 2. Exploitation or harm to children,\
|
| 108 |
+
\ including the solicitation, creation, acquisition, or dissemination of child exploitative\
|
| 109 |
+
\ content or failure to report Child Sexual Abuse Material\n 3. Human trafficking,\
|
| 110 |
+
\ exploitation, and sexual violence\n 4. The illegal distribution of information\
|
| 111 |
+
\ or materials to minors, including obscene materials, or failure to employ legally\
|
| 112 |
+
\ required age-gating in connection with such information or materials.\n 5.\
|
| 113 |
+
\ Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote,\
|
| 114 |
+
\ incite, or facilitate the harassment, abuse, threatening, or bullying of individuals\
|
| 115 |
+
\ or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination\
|
| 116 |
+
\ or other unlawful or harmful conduct in the provision of employment, employment\
|
| 117 |
+
\ benefits, credit, housing, other economic benefits, or other essential goods and\
|
| 118 |
+
\ services\n 4. Engage in the unauthorized or unlicensed practice of any profession\
|
| 119 |
+
\ including, but not limited to, financial, legal, medical/health, or related professional\
|
| 120 |
+
\ practices \n 5. Collect, process, disclose, generate, or infer health, demographic,\
|
| 121 |
+
\ or other sensitive personal or private information about individuals without rights\
|
| 122 |
+
\ and consents required by applicable laws\n 6. Engage in or facilitate any action\
|
| 123 |
+
\ or generate any content that infringes, misappropriates, or otherwise violates\
|
| 124 |
+
\ any third-party rights, including the outputs or results of any products or services\
|
| 125 |
+
\ using the Llama 2 Materials\n 7. Create, generate, or facilitate the creation\
|
| 126 |
+
\ of malicious code, malware, computer viruses or do anything else that could disable,\
|
| 127 |
+
\ overburden, interfere with or impair the proper working, integrity, operation\
|
| 128 |
+
\ or appearance of a website or computer system \n2. Engage in, promote, incite,\
|
| 129 |
+
\ facilitate, or assist in the planning or development of activities that present\
|
| 130 |
+
\ a risk of death or bodily harm to individuals, including use of Llama 2 related\
|
| 131 |
+
\ to the following:\n 1. Military, warfare, nuclear industries or applications,\
|
| 132 |
+
\ espionage, use for materials or activities that are subject to the International\
|
| 133 |
+
\ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
|
| 134 |
+
\ State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal\
|
| 135 |
+
\ drugs and regulated/controlled substances\n 4. Operation of critical infrastructure,\
|
| 136 |
+
\ transportation technologies, or heavy machinery\n 5. Self-harm or harm to others,\
|
| 137 |
+
\ including suicide, cutting, and eating disorders\n 6. Any content intended to\
|
| 138 |
+
\ incite or promote violence, abuse, or any infliction of bodily harm to an individual\n\
|
| 139 |
+
3. Intentionally deceive or mislead others, including use of Llama 2 related to\
|
| 140 |
+
\ the following:\n 1. Generating, promoting, or furthering fraud or the creation\
|
| 141 |
+
\ or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory\
|
| 142 |
+
\ content, including the creation of defamatory statements, images, or other content\n\
|
| 143 |
+
\ 3. Generating, promoting, or further distributing spam\n 4. Impersonating another\
|
| 144 |
+
\ individual without consent, authorization, or legal right\n 5. Representing that\
|
| 145 |
+
\ the use of Llama 2 or outputs are human-generated\n 6. Generating or facilitating\
|
| 146 |
+
\ false online engagement, including fake reviews and other means of fake online\
|
| 147 |
+
\ engagement \n 4. Fail to appropriately disclose to end users any known dangers\
|
| 148 |
+
\ of your AI system \nPlease report any violation of this Policy, software “bug,”\
|
| 149 |
+
\ or other problems that could lead to a violation of this Policy through one of\
|
| 150 |
+
\ the following means: * Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)\
|
| 151 |
+
\ * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\
|
| 152 |
+
\ * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\
|
| 153 |
+
\ * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama:\
|
| 154 |
+
\ [LlamaUseReport@meta.com](mailto:LlamaUseReport@meta.com)"
|
| 155 |
+
extra_gated_fields:
|
| 156 |
+
First Name: text
|
| 157 |
+
Last Name: text
|
| 158 |
+
Date of birth: date_picker
|
| 159 |
+
Country: country
|
| 160 |
+
Affiliation: text
|
| 161 |
+
geo: ip_location
|
| 162 |
+
? By clicking Submit below I accept the terms of the license and acknowledge that
|
| 163 |
+
the information I provide will be collected stored processed and shared in accordance
|
| 164 |
+
with the Meta Privacy Policy
|
| 165 |
+
: checkbox
|
| 166 |
+
extra_gated_description: The information you provide will be collected, stored, processed
|
| 167 |
+
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
|
| 168 |
+
extra_gated_button_content: Submit
|
| 169 |
+
---
|
| 170 |
+
|
| 171 |
+
# ipetrukha/CodeLlama-7b-Instruct-hf-4bit
|
| 172 |
+
|
| 173 |
+
The Model [ipetrukha/CodeLlama-7b-Instruct-hf-4bit](https://huggingface.co/ipetrukha/CodeLlama-7b-Instruct-hf-4bit) was converted to MLX format from [meta-llama/CodeLlama-7b-Instruct-hf](https://huggingface.co/meta-llama/CodeLlama-7b-Instruct-hf) using mlx-lm version **0.16.1**.
|
| 174 |
+
|
| 175 |
+
## Use with mlx
|
| 176 |
+
|
| 177 |
+
```bash
|
| 178 |
+
pip install mlx-lm
|
| 179 |
+
```
|
| 180 |
+
|
| 181 |
+
```python
|
| 182 |
+
from mlx_lm import load, generate
|
| 183 |
+
|
| 184 |
+
model, tokenizer = load("ipetrukha/CodeLlama-7b-Instruct-hf-4bit")
|
| 185 |
+
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
| 186 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 1,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"hidden_act": "silu",
|
| 8 |
+
"hidden_size": 4096,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"intermediate_size": 11008,
|
| 11 |
+
"max_position_embeddings": 16384,
|
| 12 |
+
"model_type": "llama",
|
| 13 |
+
"num_attention_heads": 32,
|
| 14 |
+
"num_hidden_layers": 32,
|
| 15 |
+
"num_key_value_heads": 32,
|
| 16 |
+
"pretraining_tp": 1,
|
| 17 |
+
"quantization": {
|
| 18 |
+
"group_size": 64,
|
| 19 |
+
"bits": 4
|
| 20 |
+
},
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 1000000,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.33.0.dev0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 32016
|
| 29 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7053f6d78e0ea1f148187f36cea6d15d5777f071e04199f096cc205efd1d7f3f
|
| 3 |
+
size 3790899435
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,750 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 3790815232
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.biases": "model.safetensors",
|
| 7 |
+
"lm_head.scales": "model.safetensors",
|
| 8 |
+
"lm_head.weight": "model.safetensors",
|
| 9 |
+
"model.embed_tokens.biases": "model.safetensors",
|
| 10 |
+
"model.embed_tokens.scales": "model.safetensors",
|
| 11 |
+
"model.embed_tokens.weight": "model.safetensors",
|
| 12 |
+
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
| 13 |
+
"model.layers.0.mlp.down_proj.biases": "model.safetensors",
|
| 14 |
+
"model.layers.0.mlp.down_proj.scales": "model.safetensors",
|
| 15 |
+
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
| 16 |
+
"model.layers.0.mlp.gate_proj.biases": "model.safetensors",
|
| 17 |
+
"model.layers.0.mlp.gate_proj.scales": "model.safetensors",
|
| 18 |
+
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
| 19 |
+
"model.layers.0.mlp.up_proj.biases": "model.safetensors",
|
| 20 |
+
"model.layers.0.mlp.up_proj.scales": "model.safetensors",
|
| 21 |
+
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
| 22 |
+
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.k_proj.biases": "model.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.k_proj.scales": "model.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
| 26 |
+
"model.layers.0.self_attn.o_proj.biases": "model.safetensors",
|
| 27 |
+
"model.layers.0.self_attn.o_proj.scales": "model.safetensors",
|
| 28 |
+
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
| 29 |
+
"model.layers.0.self_attn.q_proj.biases": "model.safetensors",
|
| 30 |
+
"model.layers.0.self_attn.q_proj.scales": "model.safetensors",
|
| 31 |
+
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
| 32 |
+
"model.layers.0.self_attn.v_proj.biases": "model.safetensors",
|
| 33 |
+
"model.layers.0.self_attn.v_proj.scales": "model.safetensors",
|
| 34 |
+
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
| 35 |
+
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
| 36 |
+
"model.layers.1.mlp.down_proj.biases": "model.safetensors",
|
| 37 |
+
"model.layers.1.mlp.down_proj.scales": "model.safetensors",
|
| 38 |
+
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
| 39 |
+
"model.layers.1.mlp.gate_proj.biases": "model.safetensors",
|
| 40 |
+
"model.layers.1.mlp.gate_proj.scales": "model.safetensors",
|
| 41 |
+
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
| 42 |
+
"model.layers.1.mlp.up_proj.biases": "model.safetensors",
|
| 43 |
+
"model.layers.1.mlp.up_proj.scales": "model.safetensors",
|
| 44 |
+
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
| 45 |
+
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
| 46 |
+
"model.layers.1.self_attn.k_proj.biases": "model.safetensors",
|
| 47 |
+
"model.layers.1.self_attn.k_proj.scales": "model.safetensors",
|
| 48 |
+
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
| 49 |
+
"model.layers.1.self_attn.o_proj.biases": "model.safetensors",
|
| 50 |
+
"model.layers.1.self_attn.o_proj.scales": "model.safetensors",
|
| 51 |
+
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
| 52 |
+
"model.layers.1.self_attn.q_proj.biases": "model.safetensors",
|
| 53 |
+
"model.layers.1.self_attn.q_proj.scales": "model.safetensors",
|
| 54 |
+
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
| 55 |
+
"model.layers.1.self_attn.v_proj.biases": "model.safetensors",
|
| 56 |
+
"model.layers.1.self_attn.v_proj.scales": "model.safetensors",
|
| 57 |
+
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
| 58 |
+
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
| 59 |
+
"model.layers.10.mlp.down_proj.biases": "model.safetensors",
|
| 60 |
+
"model.layers.10.mlp.down_proj.scales": "model.safetensors",
|
| 61 |
+
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
| 62 |
+
"model.layers.10.mlp.gate_proj.biases": "model.safetensors",
|
| 63 |
+
"model.layers.10.mlp.gate_proj.scales": "model.safetensors",
|
| 64 |
+
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
| 65 |
+
"model.layers.10.mlp.up_proj.biases": "model.safetensors",
|
| 66 |
+
"model.layers.10.mlp.up_proj.scales": "model.safetensors",
|
| 67 |
+
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
| 68 |
+
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
| 69 |
+
"model.layers.10.self_attn.k_proj.biases": "model.safetensors",
|
| 70 |
+
"model.layers.10.self_attn.k_proj.scales": "model.safetensors",
|
| 71 |
+
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
| 72 |
+
"model.layers.10.self_attn.o_proj.biases": "model.safetensors",
|
| 73 |
+
"model.layers.10.self_attn.o_proj.scales": "model.safetensors",
|
| 74 |
+
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
| 75 |
+
"model.layers.10.self_attn.q_proj.biases": "model.safetensors",
|
| 76 |
+
"model.layers.10.self_attn.q_proj.scales": "model.safetensors",
|
| 77 |
+
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
| 78 |
+
"model.layers.10.self_attn.v_proj.biases": "model.safetensors",
|
| 79 |
+
"model.layers.10.self_attn.v_proj.scales": "model.safetensors",
|
| 80 |
+
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
| 81 |
+
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
| 82 |
+
"model.layers.11.mlp.down_proj.biases": "model.safetensors",
|
| 83 |
+
"model.layers.11.mlp.down_proj.scales": "model.safetensors",
|
| 84 |
+
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
| 85 |
+
"model.layers.11.mlp.gate_proj.biases": "model.safetensors",
|
| 86 |
+
"model.layers.11.mlp.gate_proj.scales": "model.safetensors",
|
| 87 |
+
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
| 88 |
+
"model.layers.11.mlp.up_proj.biases": "model.safetensors",
|
| 89 |
+
"model.layers.11.mlp.up_proj.scales": "model.safetensors",
|
| 90 |
+
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
| 91 |
+
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
| 92 |
+
"model.layers.11.self_attn.k_proj.biases": "model.safetensors",
|
| 93 |
+
"model.layers.11.self_attn.k_proj.scales": "model.safetensors",
|
| 94 |
+
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
| 95 |
+
"model.layers.11.self_attn.o_proj.biases": "model.safetensors",
|
| 96 |
+
"model.layers.11.self_attn.o_proj.scales": "model.safetensors",
|
| 97 |
+
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
| 98 |
+
"model.layers.11.self_attn.q_proj.biases": "model.safetensors",
|
| 99 |
+
"model.layers.11.self_attn.q_proj.scales": "model.safetensors",
|
| 100 |
+
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
| 101 |
+
"model.layers.11.self_attn.v_proj.biases": "model.safetensors",
|
| 102 |
+
"model.layers.11.self_attn.v_proj.scales": "model.safetensors",
|
| 103 |
+
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
| 104 |
+
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
| 105 |
+
"model.layers.12.mlp.down_proj.biases": "model.safetensors",
|
| 106 |
+
"model.layers.12.mlp.down_proj.scales": "model.safetensors",
|
| 107 |
+
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
| 108 |
+
"model.layers.12.mlp.gate_proj.biases": "model.safetensors",
|
| 109 |
+
"model.layers.12.mlp.gate_proj.scales": "model.safetensors",
|
| 110 |
+
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
| 111 |
+
"model.layers.12.mlp.up_proj.biases": "model.safetensors",
|
| 112 |
+
"model.layers.12.mlp.up_proj.scales": "model.safetensors",
|
| 113 |
+
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
| 114 |
+
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
| 115 |
+
"model.layers.12.self_attn.k_proj.biases": "model.safetensors",
|
| 116 |
+
"model.layers.12.self_attn.k_proj.scales": "model.safetensors",
|
| 117 |
+
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
| 118 |
+
"model.layers.12.self_attn.o_proj.biases": "model.safetensors",
|
| 119 |
+
"model.layers.12.self_attn.o_proj.scales": "model.safetensors",
|
| 120 |
+
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
| 121 |
+
"model.layers.12.self_attn.q_proj.biases": "model.safetensors",
|
| 122 |
+
"model.layers.12.self_attn.q_proj.scales": "model.safetensors",
|
| 123 |
+
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
| 124 |
+
"model.layers.12.self_attn.v_proj.biases": "model.safetensors",
|
| 125 |
+
"model.layers.12.self_attn.v_proj.scales": "model.safetensors",
|
| 126 |
+
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
| 127 |
+
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
| 128 |
+
"model.layers.13.mlp.down_proj.biases": "model.safetensors",
|
| 129 |
+
"model.layers.13.mlp.down_proj.scales": "model.safetensors",
|
| 130 |
+
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
| 131 |
+
"model.layers.13.mlp.gate_proj.biases": "model.safetensors",
|
| 132 |
+
"model.layers.13.mlp.gate_proj.scales": "model.safetensors",
|
| 133 |
+
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
| 134 |
+
"model.layers.13.mlp.up_proj.biases": "model.safetensors",
|
| 135 |
+
"model.layers.13.mlp.up_proj.scales": "model.safetensors",
|
| 136 |
+
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
| 137 |
+
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
| 138 |
+
"model.layers.13.self_attn.k_proj.biases": "model.safetensors",
|
| 139 |
+
"model.layers.13.self_attn.k_proj.scales": "model.safetensors",
|
| 140 |
+
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
| 141 |
+
"model.layers.13.self_attn.o_proj.biases": "model.safetensors",
|
| 142 |
+
"model.layers.13.self_attn.o_proj.scales": "model.safetensors",
|
| 143 |
+
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
| 144 |
+
"model.layers.13.self_attn.q_proj.biases": "model.safetensors",
|
| 145 |
+
"model.layers.13.self_attn.q_proj.scales": "model.safetensors",
|
| 146 |
+
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
| 147 |
+
"model.layers.13.self_attn.v_proj.biases": "model.safetensors",
|
| 148 |
+
"model.layers.13.self_attn.v_proj.scales": "model.safetensors",
|
| 149 |
+
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
| 150 |
+
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
| 151 |
+
"model.layers.14.mlp.down_proj.biases": "model.safetensors",
|
| 152 |
+
"model.layers.14.mlp.down_proj.scales": "model.safetensors",
|
| 153 |
+
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
| 154 |
+
"model.layers.14.mlp.gate_proj.biases": "model.safetensors",
|
| 155 |
+
"model.layers.14.mlp.gate_proj.scales": "model.safetensors",
|
| 156 |
+
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
| 157 |
+
"model.layers.14.mlp.up_proj.biases": "model.safetensors",
|
| 158 |
+
"model.layers.14.mlp.up_proj.scales": "model.safetensors",
|
| 159 |
+
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
| 160 |
+
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
| 161 |
+
"model.layers.14.self_attn.k_proj.biases": "model.safetensors",
|
| 162 |
+
"model.layers.14.self_attn.k_proj.scales": "model.safetensors",
|
| 163 |
+
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
| 164 |
+
"model.layers.14.self_attn.o_proj.biases": "model.safetensors",
|
| 165 |
+
"model.layers.14.self_attn.o_proj.scales": "model.safetensors",
|
| 166 |
+
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
| 167 |
+
"model.layers.14.self_attn.q_proj.biases": "model.safetensors",
|
| 168 |
+
"model.layers.14.self_attn.q_proj.scales": "model.safetensors",
|
| 169 |
+
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
| 170 |
+
"model.layers.14.self_attn.v_proj.biases": "model.safetensors",
|
| 171 |
+
"model.layers.14.self_attn.v_proj.scales": "model.safetensors",
|
| 172 |
+
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
| 173 |
+
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
| 174 |
+
"model.layers.15.mlp.down_proj.biases": "model.safetensors",
|
| 175 |
+
"model.layers.15.mlp.down_proj.scales": "model.safetensors",
|
| 176 |
+
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
| 177 |
+
"model.layers.15.mlp.gate_proj.biases": "model.safetensors",
|
| 178 |
+
"model.layers.15.mlp.gate_proj.scales": "model.safetensors",
|
| 179 |
+
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
| 180 |
+
"model.layers.15.mlp.up_proj.biases": "model.safetensors",
|
| 181 |
+
"model.layers.15.mlp.up_proj.scales": "model.safetensors",
|
| 182 |
+
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
| 183 |
+
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
| 184 |
+
"model.layers.15.self_attn.k_proj.biases": "model.safetensors",
|
| 185 |
+
"model.layers.15.self_attn.k_proj.scales": "model.safetensors",
|
| 186 |
+
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
| 187 |
+
"model.layers.15.self_attn.o_proj.biases": "model.safetensors",
|
| 188 |
+
"model.layers.15.self_attn.o_proj.scales": "model.safetensors",
|
| 189 |
+
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
| 190 |
+
"model.layers.15.self_attn.q_proj.biases": "model.safetensors",
|
| 191 |
+
"model.layers.15.self_attn.q_proj.scales": "model.safetensors",
|
| 192 |
+
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
| 193 |
+
"model.layers.15.self_attn.v_proj.biases": "model.safetensors",
|
| 194 |
+
"model.layers.15.self_attn.v_proj.scales": "model.safetensors",
|
| 195 |
+
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
| 196 |
+
"model.layers.16.input_layernorm.weight": "model.safetensors",
|
| 197 |
+
"model.layers.16.mlp.down_proj.biases": "model.safetensors",
|
| 198 |
+
"model.layers.16.mlp.down_proj.scales": "model.safetensors",
|
| 199 |
+
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
| 200 |
+
"model.layers.16.mlp.gate_proj.biases": "model.safetensors",
|
| 201 |
+
"model.layers.16.mlp.gate_proj.scales": "model.safetensors",
|
| 202 |
+
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
| 203 |
+
"model.layers.16.mlp.up_proj.biases": "model.safetensors",
|
| 204 |
+
"model.layers.16.mlp.up_proj.scales": "model.safetensors",
|
| 205 |
+
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
| 206 |
+
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
| 207 |
+
"model.layers.16.self_attn.k_proj.biases": "model.safetensors",
|
| 208 |
+
"model.layers.16.self_attn.k_proj.scales": "model.safetensors",
|
| 209 |
+
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
| 210 |
+
"model.layers.16.self_attn.o_proj.biases": "model.safetensors",
|
| 211 |
+
"model.layers.16.self_attn.o_proj.scales": "model.safetensors",
|
| 212 |
+
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
| 213 |
+
"model.layers.16.self_attn.q_proj.biases": "model.safetensors",
|
| 214 |
+
"model.layers.16.self_attn.q_proj.scales": "model.safetensors",
|
| 215 |
+
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
| 216 |
+
"model.layers.16.self_attn.v_proj.biases": "model.safetensors",
|
| 217 |
+
"model.layers.16.self_attn.v_proj.scales": "model.safetensors",
|
| 218 |
+
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
| 219 |
+
"model.layers.17.input_layernorm.weight": "model.safetensors",
|
| 220 |
+
"model.layers.17.mlp.down_proj.biases": "model.safetensors",
|
| 221 |
+
"model.layers.17.mlp.down_proj.scales": "model.safetensors",
|
| 222 |
+
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
| 223 |
+
"model.layers.17.mlp.gate_proj.biases": "model.safetensors",
|
| 224 |
+
"model.layers.17.mlp.gate_proj.scales": "model.safetensors",
|
| 225 |
+
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
| 226 |
+
"model.layers.17.mlp.up_proj.biases": "model.safetensors",
|
| 227 |
+
"model.layers.17.mlp.up_proj.scales": "model.safetensors",
|
| 228 |
+
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
| 229 |
+
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
| 230 |
+
"model.layers.17.self_attn.k_proj.biases": "model.safetensors",
|
| 231 |
+
"model.layers.17.self_attn.k_proj.scales": "model.safetensors",
|
| 232 |
+
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
| 233 |
+
"model.layers.17.self_attn.o_proj.biases": "model.safetensors",
|
| 234 |
+
"model.layers.17.self_attn.o_proj.scales": "model.safetensors",
|
| 235 |
+
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
| 236 |
+
"model.layers.17.self_attn.q_proj.biases": "model.safetensors",
|
| 237 |
+
"model.layers.17.self_attn.q_proj.scales": "model.safetensors",
|
| 238 |
+
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
| 239 |
+
"model.layers.17.self_attn.v_proj.biases": "model.safetensors",
|
| 240 |
+
"model.layers.17.self_attn.v_proj.scales": "model.safetensors",
|
| 241 |
+
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
| 242 |
+
"model.layers.18.input_layernorm.weight": "model.safetensors",
|
| 243 |
+
"model.layers.18.mlp.down_proj.biases": "model.safetensors",
|
| 244 |
+
"model.layers.18.mlp.down_proj.scales": "model.safetensors",
|
| 245 |
+
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
| 246 |
+
"model.layers.18.mlp.gate_proj.biases": "model.safetensors",
|
| 247 |
+
"model.layers.18.mlp.gate_proj.scales": "model.safetensors",
|
| 248 |
+
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
| 249 |
+
"model.layers.18.mlp.up_proj.biases": "model.safetensors",
|
| 250 |
+
"model.layers.18.mlp.up_proj.scales": "model.safetensors",
|
| 251 |
+
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
| 252 |
+
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
| 253 |
+
"model.layers.18.self_attn.k_proj.biases": "model.safetensors",
|
| 254 |
+
"model.layers.18.self_attn.k_proj.scales": "model.safetensors",
|
| 255 |
+
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
| 256 |
+
"model.layers.18.self_attn.o_proj.biases": "model.safetensors",
|
| 257 |
+
"model.layers.18.self_attn.o_proj.scales": "model.safetensors",
|
| 258 |
+
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
| 259 |
+
"model.layers.18.self_attn.q_proj.biases": "model.safetensors",
|
| 260 |
+
"model.layers.18.self_attn.q_proj.scales": "model.safetensors",
|
| 261 |
+
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
| 262 |
+
"model.layers.18.self_attn.v_proj.biases": "model.safetensors",
|
| 263 |
+
"model.layers.18.self_attn.v_proj.scales": "model.safetensors",
|
| 264 |
+
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
| 265 |
+
"model.layers.19.input_layernorm.weight": "model.safetensors",
|
| 266 |
+
"model.layers.19.mlp.down_proj.biases": "model.safetensors",
|
| 267 |
+
"model.layers.19.mlp.down_proj.scales": "model.safetensors",
|
| 268 |
+
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
| 269 |
+
"model.layers.19.mlp.gate_proj.biases": "model.safetensors",
|
| 270 |
+
"model.layers.19.mlp.gate_proj.scales": "model.safetensors",
|
| 271 |
+
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
| 272 |
+
"model.layers.19.mlp.up_proj.biases": "model.safetensors",
|
| 273 |
+
"model.layers.19.mlp.up_proj.scales": "model.safetensors",
|
| 274 |
+
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
| 275 |
+
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
| 276 |
+
"model.layers.19.self_attn.k_proj.biases": "model.safetensors",
|
| 277 |
+
"model.layers.19.self_attn.k_proj.scales": "model.safetensors",
|
| 278 |
+
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
| 279 |
+
"model.layers.19.self_attn.o_proj.biases": "model.safetensors",
|
| 280 |
+
"model.layers.19.self_attn.o_proj.scales": "model.safetensors",
|
| 281 |
+
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
| 282 |
+
"model.layers.19.self_attn.q_proj.biases": "model.safetensors",
|
| 283 |
+
"model.layers.19.self_attn.q_proj.scales": "model.safetensors",
|
| 284 |
+
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
| 285 |
+
"model.layers.19.self_attn.v_proj.biases": "model.safetensors",
|
| 286 |
+
"model.layers.19.self_attn.v_proj.scales": "model.safetensors",
|
| 287 |
+
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
| 288 |
+
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
| 289 |
+
"model.layers.2.mlp.down_proj.biases": "model.safetensors",
|
| 290 |
+
"model.layers.2.mlp.down_proj.scales": "model.safetensors",
|
| 291 |
+
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
| 292 |
+
"model.layers.2.mlp.gate_proj.biases": "model.safetensors",
|
| 293 |
+
"model.layers.2.mlp.gate_proj.scales": "model.safetensors",
|
| 294 |
+
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
| 295 |
+
"model.layers.2.mlp.up_proj.biases": "model.safetensors",
|
| 296 |
+
"model.layers.2.mlp.up_proj.scales": "model.safetensors",
|
| 297 |
+
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
| 298 |
+
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
| 299 |
+
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
| 300 |
+
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
| 301 |
+
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 302 |
+
"model.layers.2.self_attn.o_proj.biases": "model.safetensors",
|
| 303 |
+
"model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
| 304 |
+
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
| 305 |
+
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
| 306 |
+
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
| 307 |
+
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 308 |
+
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
| 309 |
+
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
| 310 |
+
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 311 |
+
"model.layers.20.input_layernorm.weight": "model.safetensors",
|
| 312 |
+
"model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
| 313 |
+
"model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
| 314 |
+
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
| 315 |
+
"model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
| 316 |
+
"model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
| 317 |
+
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
| 318 |
+
"model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
| 319 |
+
"model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
| 320 |
+
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
| 321 |
+
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
| 322 |
+
"model.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
| 323 |
+
"model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
| 324 |
+
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
| 325 |
+
"model.layers.20.self_attn.o_proj.biases": "model.safetensors",
|
| 326 |
+
"model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
| 327 |
+
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
| 328 |
+
"model.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
| 329 |
+
"model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
| 330 |
+
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
| 331 |
+
"model.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
| 332 |
+
"model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
| 333 |
+
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 334 |
+
"model.layers.21.input_layernorm.weight": "model.safetensors",
|
| 335 |
+
"model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
| 336 |
+
"model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
| 337 |
+
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
| 338 |
+
"model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
| 339 |
+
"model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
| 340 |
+
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
| 341 |
+
"model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
| 342 |
+
"model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
| 343 |
+
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
| 344 |
+
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
| 345 |
+
"model.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
| 346 |
+
"model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
| 347 |
+
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
| 348 |
+
"model.layers.21.self_attn.o_proj.biases": "model.safetensors",
|
| 349 |
+
"model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
| 350 |
+
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
| 351 |
+
"model.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
| 352 |
+
"model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
| 353 |
+
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
| 354 |
+
"model.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
| 355 |
+
"model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
| 356 |
+
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 357 |
+
"model.layers.22.input_layernorm.weight": "model.safetensors",
|
| 358 |
+
"model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
| 359 |
+
"model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
| 360 |
+
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
| 361 |
+
"model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
| 362 |
+
"model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
| 363 |
+
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
| 364 |
+
"model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
| 365 |
+
"model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
| 366 |
+
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
| 367 |
+
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
| 368 |
+
"model.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
| 369 |
+
"model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
| 370 |
+
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
| 371 |
+
"model.layers.22.self_attn.o_proj.biases": "model.safetensors",
|
| 372 |
+
"model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
| 373 |
+
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
| 374 |
+
"model.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
| 375 |
+
"model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
| 376 |
+
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
| 377 |
+
"model.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
| 378 |
+
"model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
| 379 |
+
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 380 |
+
"model.layers.23.input_layernorm.weight": "model.safetensors",
|
| 381 |
+
"model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
| 382 |
+
"model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
| 383 |
+
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
| 384 |
+
"model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
| 385 |
+
"model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
| 386 |
+
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
| 387 |
+
"model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
| 388 |
+
"model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
| 389 |
+
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
| 390 |
+
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
| 391 |
+
"model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
| 392 |
+
"model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
| 393 |
+
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 394 |
+
"model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
| 395 |
+
"model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
| 396 |
+
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
| 397 |
+
"model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
| 398 |
+
"model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
| 399 |
+
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 400 |
+
"model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
| 401 |
+
"model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
| 402 |
+
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 403 |
+
"model.layers.24.input_layernorm.weight": "model.safetensors",
|
| 404 |
+
"model.layers.24.mlp.down_proj.biases": "model.safetensors",
|
| 405 |
+
"model.layers.24.mlp.down_proj.scales": "model.safetensors",
|
| 406 |
+
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
| 407 |
+
"model.layers.24.mlp.gate_proj.biases": "model.safetensors",
|
| 408 |
+
"model.layers.24.mlp.gate_proj.scales": "model.safetensors",
|
| 409 |
+
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
| 410 |
+
"model.layers.24.mlp.up_proj.biases": "model.safetensors",
|
| 411 |
+
"model.layers.24.mlp.up_proj.scales": "model.safetensors",
|
| 412 |
+
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
| 413 |
+
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
| 414 |
+
"model.layers.24.self_attn.k_proj.biases": "model.safetensors",
|
| 415 |
+
"model.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
| 416 |
+
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
| 417 |
+
"model.layers.24.self_attn.o_proj.biases": "model.safetensors",
|
| 418 |
+
"model.layers.24.self_attn.o_proj.scales": "model.safetensors",
|
| 419 |
+
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
| 420 |
+
"model.layers.24.self_attn.q_proj.biases": "model.safetensors",
|
| 421 |
+
"model.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
| 422 |
+
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
| 423 |
+
"model.layers.24.self_attn.v_proj.biases": "model.safetensors",
|
| 424 |
+
"model.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
| 425 |
+
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 426 |
+
"model.layers.25.input_layernorm.weight": "model.safetensors",
|
| 427 |
+
"model.layers.25.mlp.down_proj.biases": "model.safetensors",
|
| 428 |
+
"model.layers.25.mlp.down_proj.scales": "model.safetensors",
|
| 429 |
+
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
| 430 |
+
"model.layers.25.mlp.gate_proj.biases": "model.safetensors",
|
| 431 |
+
"model.layers.25.mlp.gate_proj.scales": "model.safetensors",
|
| 432 |
+
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
| 433 |
+
"model.layers.25.mlp.up_proj.biases": "model.safetensors",
|
| 434 |
+
"model.layers.25.mlp.up_proj.scales": "model.safetensors",
|
| 435 |
+
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
| 436 |
+
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
| 437 |
+
"model.layers.25.self_attn.k_proj.biases": "model.safetensors",
|
| 438 |
+
"model.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
| 439 |
+
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
| 440 |
+
"model.layers.25.self_attn.o_proj.biases": "model.safetensors",
|
| 441 |
+
"model.layers.25.self_attn.o_proj.scales": "model.safetensors",
|
| 442 |
+
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
| 443 |
+
"model.layers.25.self_attn.q_proj.biases": "model.safetensors",
|
| 444 |
+
"model.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
| 445 |
+
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
| 446 |
+
"model.layers.25.self_attn.v_proj.biases": "model.safetensors",
|
| 447 |
+
"model.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
| 448 |
+
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
| 449 |
+
"model.layers.26.input_layernorm.weight": "model.safetensors",
|
| 450 |
+
"model.layers.26.mlp.down_proj.biases": "model.safetensors",
|
| 451 |
+
"model.layers.26.mlp.down_proj.scales": "model.safetensors",
|
| 452 |
+
"model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
| 453 |
+
"model.layers.26.mlp.gate_proj.biases": "model.safetensors",
|
| 454 |
+
"model.layers.26.mlp.gate_proj.scales": "model.safetensors",
|
| 455 |
+
"model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
| 456 |
+
"model.layers.26.mlp.up_proj.biases": "model.safetensors",
|
| 457 |
+
"model.layers.26.mlp.up_proj.scales": "model.safetensors",
|
| 458 |
+
"model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
| 459 |
+
"model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
| 460 |
+
"model.layers.26.self_attn.k_proj.biases": "model.safetensors",
|
| 461 |
+
"model.layers.26.self_attn.k_proj.scales": "model.safetensors",
|
| 462 |
+
"model.layers.26.self_attn.k_proj.weight": "model.safetensors",
|
| 463 |
+
"model.layers.26.self_attn.o_proj.biases": "model.safetensors",
|
| 464 |
+
"model.layers.26.self_attn.o_proj.scales": "model.safetensors",
|
| 465 |
+
"model.layers.26.self_attn.o_proj.weight": "model.safetensors",
|
| 466 |
+
"model.layers.26.self_attn.q_proj.biases": "model.safetensors",
|
| 467 |
+
"model.layers.26.self_attn.q_proj.scales": "model.safetensors",
|
| 468 |
+
"model.layers.26.self_attn.q_proj.weight": "model.safetensors",
|
| 469 |
+
"model.layers.26.self_attn.v_proj.biases": "model.safetensors",
|
| 470 |
+
"model.layers.26.self_attn.v_proj.scales": "model.safetensors",
|
| 471 |
+
"model.layers.26.self_attn.v_proj.weight": "model.safetensors",
|
| 472 |
+
"model.layers.27.input_layernorm.weight": "model.safetensors",
|
| 473 |
+
"model.layers.27.mlp.down_proj.biases": "model.safetensors",
|
| 474 |
+
"model.layers.27.mlp.down_proj.scales": "model.safetensors",
|
| 475 |
+
"model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
| 476 |
+
"model.layers.27.mlp.gate_proj.biases": "model.safetensors",
|
| 477 |
+
"model.layers.27.mlp.gate_proj.scales": "model.safetensors",
|
| 478 |
+
"model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
| 479 |
+
"model.layers.27.mlp.up_proj.biases": "model.safetensors",
|
| 480 |
+
"model.layers.27.mlp.up_proj.scales": "model.safetensors",
|
| 481 |
+
"model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
| 482 |
+
"model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
| 483 |
+
"model.layers.27.self_attn.k_proj.biases": "model.safetensors",
|
| 484 |
+
"model.layers.27.self_attn.k_proj.scales": "model.safetensors",
|
| 485 |
+
"model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
| 486 |
+
"model.layers.27.self_attn.o_proj.biases": "model.safetensors",
|
| 487 |
+
"model.layers.27.self_attn.o_proj.scales": "model.safetensors",
|
| 488 |
+
"model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
| 489 |
+
"model.layers.27.self_attn.q_proj.biases": "model.safetensors",
|
| 490 |
+
"model.layers.27.self_attn.q_proj.scales": "model.safetensors",
|
| 491 |
+
"model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
| 492 |
+
"model.layers.27.self_attn.v_proj.biases": "model.safetensors",
|
| 493 |
+
"model.layers.27.self_attn.v_proj.scales": "model.safetensors",
|
| 494 |
+
"model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
| 495 |
+
"model.layers.28.input_layernorm.weight": "model.safetensors",
|
| 496 |
+
"model.layers.28.mlp.down_proj.biases": "model.safetensors",
|
| 497 |
+
"model.layers.28.mlp.down_proj.scales": "model.safetensors",
|
| 498 |
+
"model.layers.28.mlp.down_proj.weight": "model.safetensors",
|
| 499 |
+
"model.layers.28.mlp.gate_proj.biases": "model.safetensors",
|
| 500 |
+
"model.layers.28.mlp.gate_proj.scales": "model.safetensors",
|
| 501 |
+
"model.layers.28.mlp.gate_proj.weight": "model.safetensors",
|
| 502 |
+
"model.layers.28.mlp.up_proj.biases": "model.safetensors",
|
| 503 |
+
"model.layers.28.mlp.up_proj.scales": "model.safetensors",
|
| 504 |
+
"model.layers.28.mlp.up_proj.weight": "model.safetensors",
|
| 505 |
+
"model.layers.28.post_attention_layernorm.weight": "model.safetensors",
|
| 506 |
+
"model.layers.28.self_attn.k_proj.biases": "model.safetensors",
|
| 507 |
+
"model.layers.28.self_attn.k_proj.scales": "model.safetensors",
|
| 508 |
+
"model.layers.28.self_attn.k_proj.weight": "model.safetensors",
|
| 509 |
+
"model.layers.28.self_attn.o_proj.biases": "model.safetensors",
|
| 510 |
+
"model.layers.28.self_attn.o_proj.scales": "model.safetensors",
|
| 511 |
+
"model.layers.28.self_attn.o_proj.weight": "model.safetensors",
|
| 512 |
+
"model.layers.28.self_attn.q_proj.biases": "model.safetensors",
|
| 513 |
+
"model.layers.28.self_attn.q_proj.scales": "model.safetensors",
|
| 514 |
+
"model.layers.28.self_attn.q_proj.weight": "model.safetensors",
|
| 515 |
+
"model.layers.28.self_attn.v_proj.biases": "model.safetensors",
|
| 516 |
+
"model.layers.28.self_attn.v_proj.scales": "model.safetensors",
|
| 517 |
+
"model.layers.28.self_attn.v_proj.weight": "model.safetensors",
|
| 518 |
+
"model.layers.29.input_layernorm.weight": "model.safetensors",
|
| 519 |
+
"model.layers.29.mlp.down_proj.biases": "model.safetensors",
|
| 520 |
+
"model.layers.29.mlp.down_proj.scales": "model.safetensors",
|
| 521 |
+
"model.layers.29.mlp.down_proj.weight": "model.safetensors",
|
| 522 |
+
"model.layers.29.mlp.gate_proj.biases": "model.safetensors",
|
| 523 |
+
"model.layers.29.mlp.gate_proj.scales": "model.safetensors",
|
| 524 |
+
"model.layers.29.mlp.gate_proj.weight": "model.safetensors",
|
| 525 |
+
"model.layers.29.mlp.up_proj.biases": "model.safetensors",
|
| 526 |
+
"model.layers.29.mlp.up_proj.scales": "model.safetensors",
|
| 527 |
+
"model.layers.29.mlp.up_proj.weight": "model.safetensors",
|
| 528 |
+
"model.layers.29.post_attention_layernorm.weight": "model.safetensors",
|
| 529 |
+
"model.layers.29.self_attn.k_proj.biases": "model.safetensors",
|
| 530 |
+
"model.layers.29.self_attn.k_proj.scales": "model.safetensors",
|
| 531 |
+
"model.layers.29.self_attn.k_proj.weight": "model.safetensors",
|
| 532 |
+
"model.layers.29.self_attn.o_proj.biases": "model.safetensors",
|
| 533 |
+
"model.layers.29.self_attn.o_proj.scales": "model.safetensors",
|
| 534 |
+
"model.layers.29.self_attn.o_proj.weight": "model.safetensors",
|
| 535 |
+
"model.layers.29.self_attn.q_proj.biases": "model.safetensors",
|
| 536 |
+
"model.layers.29.self_attn.q_proj.scales": "model.safetensors",
|
| 537 |
+
"model.layers.29.self_attn.q_proj.weight": "model.safetensors",
|
| 538 |
+
"model.layers.29.self_attn.v_proj.biases": "model.safetensors",
|
| 539 |
+
"model.layers.29.self_attn.v_proj.scales": "model.safetensors",
|
| 540 |
+
"model.layers.29.self_attn.v_proj.weight": "model.safetensors",
|
| 541 |
+
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
| 542 |
+
"model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
| 543 |
+
"model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
| 544 |
+
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
| 545 |
+
"model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
| 546 |
+
"model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
| 547 |
+
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
| 548 |
+
"model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
| 549 |
+
"model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
| 550 |
+
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
| 551 |
+
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
| 552 |
+
"model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
| 553 |
+
"model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
| 554 |
+
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 555 |
+
"model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
| 556 |
+
"model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
| 557 |
+
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
| 558 |
+
"model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
| 559 |
+
"model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
| 560 |
+
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 561 |
+
"model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
| 562 |
+
"model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
| 563 |
+
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 564 |
+
"model.layers.30.input_layernorm.weight": "model.safetensors",
|
| 565 |
+
"model.layers.30.mlp.down_proj.biases": "model.safetensors",
|
| 566 |
+
"model.layers.30.mlp.down_proj.scales": "model.safetensors",
|
| 567 |
+
"model.layers.30.mlp.down_proj.weight": "model.safetensors",
|
| 568 |
+
"model.layers.30.mlp.gate_proj.biases": "model.safetensors",
|
| 569 |
+
"model.layers.30.mlp.gate_proj.scales": "model.safetensors",
|
| 570 |
+
"model.layers.30.mlp.gate_proj.weight": "model.safetensors",
|
| 571 |
+
"model.layers.30.mlp.up_proj.biases": "model.safetensors",
|
| 572 |
+
"model.layers.30.mlp.up_proj.scales": "model.safetensors",
|
| 573 |
+
"model.layers.30.mlp.up_proj.weight": "model.safetensors",
|
| 574 |
+
"model.layers.30.post_attention_layernorm.weight": "model.safetensors",
|
| 575 |
+
"model.layers.30.self_attn.k_proj.biases": "model.safetensors",
|
| 576 |
+
"model.layers.30.self_attn.k_proj.scales": "model.safetensors",
|
| 577 |
+
"model.layers.30.self_attn.k_proj.weight": "model.safetensors",
|
| 578 |
+
"model.layers.30.self_attn.o_proj.biases": "model.safetensors",
|
| 579 |
+
"model.layers.30.self_attn.o_proj.scales": "model.safetensors",
|
| 580 |
+
"model.layers.30.self_attn.o_proj.weight": "model.safetensors",
|
| 581 |
+
"model.layers.30.self_attn.q_proj.biases": "model.safetensors",
|
| 582 |
+
"model.layers.30.self_attn.q_proj.scales": "model.safetensors",
|
| 583 |
+
"model.layers.30.self_attn.q_proj.weight": "model.safetensors",
|
| 584 |
+
"model.layers.30.self_attn.v_proj.biases": "model.safetensors",
|
| 585 |
+
"model.layers.30.self_attn.v_proj.scales": "model.safetensors",
|
| 586 |
+
"model.layers.30.self_attn.v_proj.weight": "model.safetensors",
|
| 587 |
+
"model.layers.31.input_layernorm.weight": "model.safetensors",
|
| 588 |
+
"model.layers.31.mlp.down_proj.biases": "model.safetensors",
|
| 589 |
+
"model.layers.31.mlp.down_proj.scales": "model.safetensors",
|
| 590 |
+
"model.layers.31.mlp.down_proj.weight": "model.safetensors",
|
| 591 |
+
"model.layers.31.mlp.gate_proj.biases": "model.safetensors",
|
| 592 |
+
"model.layers.31.mlp.gate_proj.scales": "model.safetensors",
|
| 593 |
+
"model.layers.31.mlp.gate_proj.weight": "model.safetensors",
|
| 594 |
+
"model.layers.31.mlp.up_proj.biases": "model.safetensors",
|
| 595 |
+
"model.layers.31.mlp.up_proj.scales": "model.safetensors",
|
| 596 |
+
"model.layers.31.mlp.up_proj.weight": "model.safetensors",
|
| 597 |
+
"model.layers.31.post_attention_layernorm.weight": "model.safetensors",
|
| 598 |
+
"model.layers.31.self_attn.k_proj.biases": "model.safetensors",
|
| 599 |
+
"model.layers.31.self_attn.k_proj.scales": "model.safetensors",
|
| 600 |
+
"model.layers.31.self_attn.k_proj.weight": "model.safetensors",
|
| 601 |
+
"model.layers.31.self_attn.o_proj.biases": "model.safetensors",
|
| 602 |
+
"model.layers.31.self_attn.o_proj.scales": "model.safetensors",
|
| 603 |
+
"model.layers.31.self_attn.o_proj.weight": "model.safetensors",
|
| 604 |
+
"model.layers.31.self_attn.q_proj.biases": "model.safetensors",
|
| 605 |
+
"model.layers.31.self_attn.q_proj.scales": "model.safetensors",
|
| 606 |
+
"model.layers.31.self_attn.q_proj.weight": "model.safetensors",
|
| 607 |
+
"model.layers.31.self_attn.v_proj.biases": "model.safetensors",
|
| 608 |
+
"model.layers.31.self_attn.v_proj.scales": "model.safetensors",
|
| 609 |
+
"model.layers.31.self_attn.v_proj.weight": "model.safetensors",
|
| 610 |
+
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
| 611 |
+
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
| 612 |
+
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
| 613 |
+
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
| 614 |
+
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
| 615 |
+
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
| 616 |
+
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
| 617 |
+
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
| 618 |
+
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
| 619 |
+
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 620 |
+
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 621 |
+
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
| 622 |
+
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
| 623 |
+
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 624 |
+
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
| 625 |
+
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
| 626 |
+
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
| 627 |
+
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
| 628 |
+
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
| 629 |
+
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 630 |
+
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
| 631 |
+
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
| 632 |
+
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 633 |
+
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
| 634 |
+
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
| 635 |
+
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
| 636 |
+
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
| 637 |
+
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
| 638 |
+
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
| 639 |
+
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
| 640 |
+
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
| 641 |
+
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
| 642 |
+
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 643 |
+
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 644 |
+
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
| 645 |
+
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 646 |
+
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 647 |
+
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
| 648 |
+
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
| 649 |
+
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
| 650 |
+
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
| 651 |
+
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 652 |
+
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 653 |
+
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
| 654 |
+
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 655 |
+
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 656 |
+
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
| 657 |
+
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
| 658 |
+
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
| 659 |
+
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
| 660 |
+
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
| 661 |
+
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
| 662 |
+
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
| 663 |
+
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
| 664 |
+
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
| 665 |
+
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 666 |
+
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 667 |
+
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
| 668 |
+
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
| 669 |
+
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 670 |
+
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
| 671 |
+
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
| 672 |
+
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
| 673 |
+
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
| 674 |
+
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
| 675 |
+
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 676 |
+
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
| 677 |
+
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
| 678 |
+
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 679 |
+
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
| 680 |
+
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
| 681 |
+
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
| 682 |
+
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
| 683 |
+
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
| 684 |
+
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
| 685 |
+
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
| 686 |
+
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
| 687 |
+
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
| 688 |
+
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 689 |
+
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 690 |
+
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
| 691 |
+
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
| 692 |
+
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 693 |
+
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
| 694 |
+
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
| 695 |
+
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
| 696 |
+
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
| 697 |
+
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
| 698 |
+
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 699 |
+
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
| 700 |
+
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
| 701 |
+
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 702 |
+
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
| 703 |
+
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
| 704 |
+
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
| 705 |
+
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
| 706 |
+
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
| 707 |
+
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
| 708 |
+
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
| 709 |
+
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
| 710 |
+
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
| 711 |
+
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 712 |
+
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 713 |
+
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
| 714 |
+
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 715 |
+
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 716 |
+
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
| 717 |
+
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
| 718 |
+
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
| 719 |
+
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
| 720 |
+
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 721 |
+
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 722 |
+
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
| 723 |
+
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 724 |
+
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 725 |
+
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
| 726 |
+
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
| 727 |
+
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
| 728 |
+
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
| 729 |
+
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
| 730 |
+
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
| 731 |
+
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
| 732 |
+
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
| 733 |
+
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
| 734 |
+
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
| 735 |
+
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 736 |
+
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
| 737 |
+
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
| 738 |
+
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 739 |
+
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
| 740 |
+
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
| 741 |
+
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
| 742 |
+
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
| 743 |
+
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
| 744 |
+
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 745 |
+
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
| 746 |
+
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
| 747 |
+
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 748 |
+
"model.norm.weight": "model.safetensors"
|
| 749 |
+
}
|
| 750 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"▁<PRE>",
|
| 4 |
+
"▁<MID>",
|
| 5 |
+
"▁<SUF>",
|
| 6 |
+
"▁<EOT>"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"unk_token": {
|
| 23 |
+
"content": "<unk>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
}
|
| 29 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
|
| 3 |
+
size 500058
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32007": {
|
| 30 |
+
"content": "▁<PRE>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"32008": {
|
| 38 |
+
"content": "▁<SUF>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"32009": {
|
| 46 |
+
"content": "▁<MID>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"32010": {
|
| 54 |
+
"content": "▁<EOT>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
}
|
| 61 |
+
},
|
| 62 |
+
"additional_special_tokens": [
|
| 63 |
+
"▁<PRE>",
|
| 64 |
+
"▁<MID>",
|
| 65 |
+
"▁<SUF>",
|
| 66 |
+
"▁<EOT>"
|
| 67 |
+
],
|
| 68 |
+
"bos_token": "<s>",
|
| 69 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
|
| 70 |
+
"clean_up_tokenization_spaces": false,
|
| 71 |
+
"eos_token": "</s>",
|
| 72 |
+
"eot_token": "▁<EOT>",
|
| 73 |
+
"fill_token": "<FILL_ME>",
|
| 74 |
+
"legacy": null,
|
| 75 |
+
"middle_token": "▁<MID>",
|
| 76 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 77 |
+
"pad_token": null,
|
| 78 |
+
"prefix_token": "▁<PRE>",
|
| 79 |
+
"sp_model_kwargs": {},
|
| 80 |
+
"suffix_token": "▁<SUF>",
|
| 81 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
| 82 |
+
"unk_token": "<unk>",
|
| 83 |
+
"use_default_system_prompt": false
|
| 84 |
+
}
|