Upload folder using huggingface_hub
#1
by
prince-canuma
- opened
- README.md +273 -0
- config.json +34 -0
- model.safetensors +3 -0
- model.safetensors.index.json +842 -0
README.md
ADDED
|
@@ -0,0 +1,273 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Ministral-8B-Instruct-2410-HF
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- fr
|
| 6 |
+
- de
|
| 7 |
+
- es
|
| 8 |
+
- it
|
| 9 |
+
- pt
|
| 10 |
+
- zh
|
| 11 |
+
- ja
|
| 12 |
+
- ru
|
| 13 |
+
- ko
|
| 14 |
+
library_name: vllm
|
| 15 |
+
license: other
|
| 16 |
+
license_name: mrl
|
| 17 |
+
license_link: https://mistral.ai/licenses/MRL-0.1.md
|
| 18 |
+
tags:
|
| 19 |
+
- mlx
|
| 20 |
+
inference: false
|
| 21 |
+
extra_gated_prompt: '# Mistral AI Research License
|
| 22 |
+
|
| 23 |
+
If You want to use a Mistral Model, a Derivative or an Output for any purpose that
|
| 24 |
+
is not expressly authorized under this Agreement, You must request a license from
|
| 25 |
+
Mistral AI, which Mistral AI may grant to You in Mistral AI''s sole discretion.
|
| 26 |
+
To discuss such a license, please contact Mistral AI via the website contact form:
|
| 27 |
+
https://mistral.ai/contact/
|
| 28 |
+
|
| 29 |
+
## 1. Scope and acceptance
|
| 30 |
+
|
| 31 |
+
**1.1. Scope of the Agreement.** This Agreement applies to any use, modification,
|
| 32 |
+
or Distribution of any Mistral Model by You, regardless of the source You obtained
|
| 33 |
+
a copy of such Mistral Model.
|
| 34 |
+
|
| 35 |
+
**1.2. Acceptance.** By accessing, using, modifying, Distributing a Mistral Model,
|
| 36 |
+
or by creating, using or distributing a Derivative of the Mistral Model, You agree
|
| 37 |
+
to be bound by this Agreement.
|
| 38 |
+
|
| 39 |
+
**1.3. Acceptance on behalf of a third-party.** If You accept this Agreement on
|
| 40 |
+
behalf of Your employer or another person or entity, You warrant and represent that
|
| 41 |
+
You have the authority to act and accept this Agreement on their behalf. In such
|
| 42 |
+
a case, the word "You" in this Agreement will refer to Your employer or such other
|
| 43 |
+
person or entity.
|
| 44 |
+
|
| 45 |
+
## 2. License
|
| 46 |
+
|
| 47 |
+
**2.1. Grant of rights**. Subject to Section 3 below, Mistral AI hereby grants
|
| 48 |
+
You a non-exclusive, royalty-free, worldwide, non-sublicensable, non-transferable,
|
| 49 |
+
limited license to use, copy, modify, and Distribute under the conditions provided
|
| 50 |
+
in Section 2.2 below, the Mistral Model and any Derivatives made by or for Mistral
|
| 51 |
+
AI and to create Derivatives of the Mistral Model.
|
| 52 |
+
|
| 53 |
+
**2.2. Distribution of Mistral Model and Derivatives made by or for Mistral AI.**
|
| 54 |
+
Subject to Section 3 below, You may Distribute copies of the Mistral Model and/or
|
| 55 |
+
Derivatives made by or for Mistral AI, under the following conditions: You must
|
| 56 |
+
make available a copy of this Agreement to third-party recipients of the Mistral
|
| 57 |
+
Models and/or Derivatives made by or for Mistral AI you Distribute, it being specified
|
| 58 |
+
that any rights to use the Mistral Models and/or Derivatives made by or for Mistral
|
| 59 |
+
AI shall be directly granted by Mistral AI to said third-party recipients pursuant
|
| 60 |
+
to the Mistral AI Research License agreement executed between these parties; You
|
| 61 |
+
must retain in all copies of the Mistral Models the following attribution notice
|
| 62 |
+
within a "Notice" text file distributed as part of such copies: "Licensed by Mistral
|
| 63 |
+
AI under the Mistral AI Research License".
|
| 64 |
+
|
| 65 |
+
**2.3. Distribution of Derivatives made by or for You.** Subject to Section 3 below,
|
| 66 |
+
You may Distribute any Derivatives made by or for You under additional or different
|
| 67 |
+
terms and conditions, provided that: In any event, the use and modification of Mistral
|
| 68 |
+
Model and/or Derivatives made by or for Mistral AI shall remain governed by the
|
| 69 |
+
terms and conditions of this Agreement; You include in any such Derivatives made
|
| 70 |
+
by or for You prominent notices stating that You modified the concerned Mistral
|
| 71 |
+
Model; and Any terms and conditions You impose on any third-party recipients relating
|
| 72 |
+
to Derivatives made by or for You shall neither limit such third-party recipients''
|
| 73 |
+
use of the Mistral Model or any Derivatives made by or for Mistral AI in accordance
|
| 74 |
+
with the Mistral AI Research License nor conflict with any of its terms and conditions.
|
| 75 |
+
|
| 76 |
+
## 3. Limitations
|
| 77 |
+
|
| 78 |
+
**3.1. Misrepresentation.** You must not misrepresent or imply, through any means,
|
| 79 |
+
that the Derivatives made by or for You and/or any modified version of the Mistral
|
| 80 |
+
Model You Distribute under your name and responsibility is an official product of
|
| 81 |
+
Mistral AI or has been endorsed, approved or validated by Mistral AI, unless You
|
| 82 |
+
are authorized by Us to do so in writing.
|
| 83 |
+
|
| 84 |
+
**3.2. Usage Limitation.** You shall only use the Mistral Models, Derivatives (whether
|
| 85 |
+
or not created by Mistral AI) and Outputs for Research Purposes.
|
| 86 |
+
|
| 87 |
+
## 4. Intellectual Property
|
| 88 |
+
|
| 89 |
+
**4.1. Trademarks.** No trademark licenses are granted under this Agreement, and
|
| 90 |
+
in connection with the Mistral Models, You may not use any name or mark owned by
|
| 91 |
+
or associated with Mistral AI or any of its affiliates, except (i) as required for
|
| 92 |
+
reasonable and customary use in describing and Distributing the Mistral Models and
|
| 93 |
+
Derivatives made by or for Mistral AI and (ii) for attribution purposes as required
|
| 94 |
+
by this Agreement.
|
| 95 |
+
|
| 96 |
+
**4.2. Outputs.** We claim no ownership rights in and to the Outputs. You are solely
|
| 97 |
+
responsible for the Outputs You generate and their subsequent uses in accordance
|
| 98 |
+
with this Agreement. Any Outputs shall be subject to the restrictions set out in
|
| 99 |
+
Section 3 of this Agreement.
|
| 100 |
+
|
| 101 |
+
**4.3. Derivatives.** By entering into this Agreement, You accept that any Derivatives
|
| 102 |
+
that You may create or that may be created for You shall be subject to the restrictions
|
| 103 |
+
set out in Section 3 of this Agreement.
|
| 104 |
+
|
| 105 |
+
## 5. Liability
|
| 106 |
+
|
| 107 |
+
**5.1. Limitation of liability.** In no event, unless required by applicable law
|
| 108 |
+
(such as deliberate and grossly negligent acts) or agreed to in writing, shall Mistral
|
| 109 |
+
AI be liable to You for damages, including any direct, indirect, special, incidental,
|
| 110 |
+
or consequential damages of any character arising as a result of this Agreement
|
| 111 |
+
or out of the use or inability to use the Mistral Models and Derivatives (including
|
| 112 |
+
but not limited to damages for loss of data, loss of goodwill, loss of expected
|
| 113 |
+
profit or savings, work stoppage, computer failure or malfunction, or any damage
|
| 114 |
+
caused by malware or security breaches), even if Mistral AI has been advised of
|
| 115 |
+
the possibility of such damages.
|
| 116 |
+
|
| 117 |
+
**5.2. Indemnification.** You agree to indemnify and hold harmless Mistral AI from
|
| 118 |
+
and against any claims, damages, or losses arising out of or related to Your use
|
| 119 |
+
or Distribution of the Mistral Models and Derivatives.
|
| 120 |
+
|
| 121 |
+
## 6. Warranty
|
| 122 |
+
|
| 123 |
+
**6.1. Disclaimer.** Unless required by applicable law or prior agreed to by Mistral
|
| 124 |
+
AI in writing, Mistral AI provides the Mistral Models and Derivatives on an "AS
|
| 125 |
+
IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied,
|
| 126 |
+
including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT,
|
| 127 |
+
MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. Mistral AI does not represent
|
| 128 |
+
nor warrant that the Mistral Models and Derivatives will be error-free, meet Your
|
| 129 |
+
or any third party''s requirements, be secure or will allow You or any third party
|
| 130 |
+
to achieve any kind of result or generate any kind of content. You are solely responsible
|
| 131 |
+
for determining the appropriateness of using or Distributing the Mistral Models
|
| 132 |
+
and Derivatives and assume any risks associated with Your exercise of rights under
|
| 133 |
+
this Agreement.
|
| 134 |
+
|
| 135 |
+
## 7. Termination
|
| 136 |
+
|
| 137 |
+
**7.1. Term.** This Agreement is effective as of the date of your acceptance of
|
| 138 |
+
this Agreement or access to the concerned Mistral Models or Derivatives and will
|
| 139 |
+
continue until terminated in accordance with the following terms.
|
| 140 |
+
|
| 141 |
+
**7.2. Termination.** Mistral AI may terminate this Agreement at any time if You
|
| 142 |
+
are in breach of this Agreement. Upon termination of this Agreement, You must cease
|
| 143 |
+
to use all Mistral Models and Derivatives and shall permanently delete any copy
|
| 144 |
+
thereof. The following provisions, in their relevant parts, will survive any termination
|
| 145 |
+
or expiration of this Agreement, each for the duration necessary to achieve its
|
| 146 |
+
own intended purpose (e.g. the liability provision will survive until the end of
|
| 147 |
+
the applicable limitation period):Sections 5 (Liability), 6(Warranty), 7 (Termination)
|
| 148 |
+
and 8 (General Provisions).
|
| 149 |
+
|
| 150 |
+
**7.3. Litigation.** If You initiate any legal action or proceedings against Us
|
| 151 |
+
or any other entity (including a cross-claim or counterclaim in a lawsuit), alleging
|
| 152 |
+
that the Model or a Derivative, or any part thereof, infringe upon intellectual
|
| 153 |
+
property or other rights owned or licensable by You, then any licenses granted to
|
| 154 |
+
You under this Agreement will immediately terminate as of the date such legal action
|
| 155 |
+
or claim is filed or initiated.
|
| 156 |
+
|
| 157 |
+
## 8. General provisions
|
| 158 |
+
|
| 159 |
+
**8.1. Governing laws.** This Agreement will be governed by the laws of France,
|
| 160 |
+
without regard to choice of law principles, and the UN Convention on Contracts for
|
| 161 |
+
the International Sale of Goods does not apply to this Agreement.
|
| 162 |
+
|
| 163 |
+
**8.2. Competent jurisdiction.** The courts of Paris shall have exclusive jurisdiction
|
| 164 |
+
of any dispute arising out of this Agreement.
|
| 165 |
+
|
| 166 |
+
**8.3. Severability.** If any provision of this Agreement is held to be invalid,
|
| 167 |
+
illegal or unenforceable, the remaining provisions shall be unaffected thereby and
|
| 168 |
+
remain valid as if such provision had not been set forth herein.
|
| 169 |
+
|
| 170 |
+
## 9. Definitions
|
| 171 |
+
|
| 172 |
+
"Agreement": means this Mistral AI Research License agreement governing the access,
|
| 173 |
+
use, and Distribution of the Mistral Models, Derivatives and Outputs.
|
| 174 |
+
|
| 175 |
+
"Derivative": means any (i) modified version of the Mistral Model (including but
|
| 176 |
+
not limited to any customized or fine-tuned version thereof), (ii) work based on
|
| 177 |
+
the Mistral Model, or (iii) any other derivative work thereof.
|
| 178 |
+
|
| 179 |
+
"Distribution", "Distributing", "Distribute" or "Distributed": means supplying,
|
| 180 |
+
providing or making available, by any means, a copy of the Mistral Models and/or
|
| 181 |
+
the Derivatives as the case may be, subject to Section 3 of this Agreement.
|
| 182 |
+
|
| 183 |
+
"Mistral AI", "We" or "Us": means Mistral AI, a French société par actions simplifiée
|
| 184 |
+
registered in the Paris commercial registry under the number 952 418 325, and having
|
| 185 |
+
its registered seat at 15, rue des Halles, 75001 Paris.
|
| 186 |
+
|
| 187 |
+
"Mistral Model": means the foundational large language model(s), and its elements
|
| 188 |
+
which include algorithms, software, instructed checkpoints, parameters, source code
|
| 189 |
+
(inference code, evaluation code and, if applicable, fine-tuning code) and any other
|
| 190 |
+
elements associated thereto made available by Mistral AI under this Agreement, including,
|
| 191 |
+
if any, the technical documentation, manuals and instructions for the use and operation
|
| 192 |
+
thereof.
|
| 193 |
+
|
| 194 |
+
"Research Purposes": means any use of a Mistral Model, Derivative, or Output that
|
| 195 |
+
is solely for (a) personal, scientific or academic research, and (b) for non-profit
|
| 196 |
+
and non-commercial purposes, and not directly or indirectly connected to any commercial
|
| 197 |
+
activities or business operations. For illustration purposes, Research Purposes
|
| 198 |
+
does not include (1) any usage of the Mistral Model, Derivative or Output by individuals
|
| 199 |
+
or contractors employed in or engaged by companies in the context of (a) their daily
|
| 200 |
+
tasks, or (b) any activity (including but not limited to any testing or proof-of-concept)
|
| 201 |
+
that is intended to generate revenue, nor (2) any Distribution by a commercial entity
|
| 202 |
+
of the Mistral Model, Derivative or Output whether in return for payment or free
|
| 203 |
+
of charge, in any medium or form, including but not limited to through a hosted
|
| 204 |
+
or managed service (e.g. SaaS, cloud instances, etc.), or behind a software layer.
|
| 205 |
+
|
| 206 |
+
"Outputs": means any content generated by the operation of the Mistral Models or
|
| 207 |
+
the Derivatives from a prompt (i.e., text instructions) provided by users. For
|
| 208 |
+
the avoidance of doubt, Outputs do not include any components of a Mistral Models,
|
| 209 |
+
such as any fine-tuned versions of the Mistral Models, the weights, or parameters.
|
| 210 |
+
|
| 211 |
+
"You": means the individual or entity entering into this Agreement with Mistral
|
| 212 |
+
AI.
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
*Mistral AI processes your personal data below to provide the model and enforce
|
| 216 |
+
its license. If you are affiliated with a commercial entity, we may also send you
|
| 217 |
+
communications about our models. For more information on your rights and data handling,
|
| 218 |
+
please see our <a href="https://mistral.ai/terms/">privacy policy</a>.*'
|
| 219 |
+
extra_gated_fields:
|
| 220 |
+
First Name: text
|
| 221 |
+
Last Name: text
|
| 222 |
+
Country: country
|
| 223 |
+
Affiliation: text
|
| 224 |
+
Job title: text
|
| 225 |
+
I understand that I can only use the model, any derivative versions and their outputs for non-commercial research purposes: checkbox
|
| 226 |
+
? I understand that if I am a commercial entity, I am not permitted to use or distribute
|
| 227 |
+
the model internally or externally, or expose it in my own offerings without a
|
| 228 |
+
commercial license
|
| 229 |
+
: checkbox
|
| 230 |
+
? I understand that if I upload the model, or any derivative version, on any platform,
|
| 231 |
+
I must include the Mistral Research License
|
| 232 |
+
: checkbox
|
| 233 |
+
? I understand that for commercial use of the model, I can contact Mistral or use
|
| 234 |
+
the Mistral AI API on la Plateforme or any of our cloud provider partners
|
| 235 |
+
: checkbox
|
| 236 |
+
? By clicking Submit below I accept the terms of the license and acknowledge that
|
| 237 |
+
the information I provide will be collected stored processed and shared in accordance
|
| 238 |
+
with the Mistral Privacy Policy
|
| 239 |
+
: checkbox
|
| 240 |
+
geo: ip_location
|
| 241 |
+
extra_gated_description: Mistral AI processes your personal data below to provide
|
| 242 |
+
the model and enforce its license. If you are affiliated with a commercial entity,
|
| 243 |
+
we may also send you communications about our models. For more information on your
|
| 244 |
+
rights and data handling, please see our <a href="https://mistral.ai/terms/">privacy
|
| 245 |
+
policy</a>.
|
| 246 |
+
extra_gated_button_content: Submit
|
| 247 |
+
---
|
| 248 |
+
|
| 249 |
+
# mlx-community/Ministral-8B-Instruct-2410-4bit
|
| 250 |
+
|
| 251 |
+
The Model [mlx-community/Ministral-8B-Instruct-2410-4bit](https://huggingface.co/mlx-community/Ministral-8B-Instruct-2410-4bit) was converted to MLX format from [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) using mlx-lm version **0.19.1**.
|
| 252 |
+
|
| 253 |
+
## Use with mlx
|
| 254 |
+
|
| 255 |
+
```bash
|
| 256 |
+
pip install mlx-lm
|
| 257 |
+
```
|
| 258 |
+
|
| 259 |
+
```python
|
| 260 |
+
from mlx_lm import load, generate
|
| 261 |
+
|
| 262 |
+
model, tokenizer = load("mlx-community/Ministral-8B-Instruct-2410-4bit")
|
| 263 |
+
|
| 264 |
+
prompt="hello"
|
| 265 |
+
|
| 266 |
+
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
|
| 267 |
+
messages = [{"role": "user", "content": prompt}]
|
| 268 |
+
prompt = tokenizer.apply_chat_template(
|
| 269 |
+
messages, tokenize=False, add_generation_prompt=True
|
| 270 |
+
)
|
| 271 |
+
|
| 272 |
+
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
| 273 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MistralForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"head_dim": 128,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 12288,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"model_type": "mistral",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 36,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"quantization": {
|
| 19 |
+
"group_size": 64,
|
| 20 |
+
"bits": 4
|
| 21 |
+
},
|
| 22 |
+
"quantization_config": {
|
| 23 |
+
"group_size": 64,
|
| 24 |
+
"bits": 4
|
| 25 |
+
},
|
| 26 |
+
"rms_norm_eps": 1e-05,
|
| 27 |
+
"rope_theta": 100000000.0,
|
| 28 |
+
"sliding_window": null,
|
| 29 |
+
"tie_word_embeddings": false,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.44.0",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 131072
|
| 34 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7049798d4a6002e3d8df810b9a31c4fe4846d35a88c7b947abe6ce5222498b16
|
| 3 |
+
size 4511666793
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,842 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 4511571968
|
| 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.32.input_layernorm.weight": "model.safetensors",
|
| 611 |
+
"model.layers.32.mlp.down_proj.biases": "model.safetensors",
|
| 612 |
+
"model.layers.32.mlp.down_proj.scales": "model.safetensors",
|
| 613 |
+
"model.layers.32.mlp.down_proj.weight": "model.safetensors",
|
| 614 |
+
"model.layers.32.mlp.gate_proj.biases": "model.safetensors",
|
| 615 |
+
"model.layers.32.mlp.gate_proj.scales": "model.safetensors",
|
| 616 |
+
"model.layers.32.mlp.gate_proj.weight": "model.safetensors",
|
| 617 |
+
"model.layers.32.mlp.up_proj.biases": "model.safetensors",
|
| 618 |
+
"model.layers.32.mlp.up_proj.scales": "model.safetensors",
|
| 619 |
+
"model.layers.32.mlp.up_proj.weight": "model.safetensors",
|
| 620 |
+
"model.layers.32.post_attention_layernorm.weight": "model.safetensors",
|
| 621 |
+
"model.layers.32.self_attn.k_proj.biases": "model.safetensors",
|
| 622 |
+
"model.layers.32.self_attn.k_proj.scales": "model.safetensors",
|
| 623 |
+
"model.layers.32.self_attn.k_proj.weight": "model.safetensors",
|
| 624 |
+
"model.layers.32.self_attn.o_proj.biases": "model.safetensors",
|
| 625 |
+
"model.layers.32.self_attn.o_proj.scales": "model.safetensors",
|
| 626 |
+
"model.layers.32.self_attn.o_proj.weight": "model.safetensors",
|
| 627 |
+
"model.layers.32.self_attn.q_proj.biases": "model.safetensors",
|
| 628 |
+
"model.layers.32.self_attn.q_proj.scales": "model.safetensors",
|
| 629 |
+
"model.layers.32.self_attn.q_proj.weight": "model.safetensors",
|
| 630 |
+
"model.layers.32.self_attn.v_proj.biases": "model.safetensors",
|
| 631 |
+
"model.layers.32.self_attn.v_proj.scales": "model.safetensors",
|
| 632 |
+
"model.layers.32.self_attn.v_proj.weight": "model.safetensors",
|
| 633 |
+
"model.layers.33.input_layernorm.weight": "model.safetensors",
|
| 634 |
+
"model.layers.33.mlp.down_proj.biases": "model.safetensors",
|
| 635 |
+
"model.layers.33.mlp.down_proj.scales": "model.safetensors",
|
| 636 |
+
"model.layers.33.mlp.down_proj.weight": "model.safetensors",
|
| 637 |
+
"model.layers.33.mlp.gate_proj.biases": "model.safetensors",
|
| 638 |
+
"model.layers.33.mlp.gate_proj.scales": "model.safetensors",
|
| 639 |
+
"model.layers.33.mlp.gate_proj.weight": "model.safetensors",
|
| 640 |
+
"model.layers.33.mlp.up_proj.biases": "model.safetensors",
|
| 641 |
+
"model.layers.33.mlp.up_proj.scales": "model.safetensors",
|
| 642 |
+
"model.layers.33.mlp.up_proj.weight": "model.safetensors",
|
| 643 |
+
"model.layers.33.post_attention_layernorm.weight": "model.safetensors",
|
| 644 |
+
"model.layers.33.self_attn.k_proj.biases": "model.safetensors",
|
| 645 |
+
"model.layers.33.self_attn.k_proj.scales": "model.safetensors",
|
| 646 |
+
"model.layers.33.self_attn.k_proj.weight": "model.safetensors",
|
| 647 |
+
"model.layers.33.self_attn.o_proj.biases": "model.safetensors",
|
| 648 |
+
"model.layers.33.self_attn.o_proj.scales": "model.safetensors",
|
| 649 |
+
"model.layers.33.self_attn.o_proj.weight": "model.safetensors",
|
| 650 |
+
"model.layers.33.self_attn.q_proj.biases": "model.safetensors",
|
| 651 |
+
"model.layers.33.self_attn.q_proj.scales": "model.safetensors",
|
| 652 |
+
"model.layers.33.self_attn.q_proj.weight": "model.safetensors",
|
| 653 |
+
"model.layers.33.self_attn.v_proj.biases": "model.safetensors",
|
| 654 |
+
"model.layers.33.self_attn.v_proj.scales": "model.safetensors",
|
| 655 |
+
"model.layers.33.self_attn.v_proj.weight": "model.safetensors",
|
| 656 |
+
"model.layers.34.input_layernorm.weight": "model.safetensors",
|
| 657 |
+
"model.layers.34.mlp.down_proj.biases": "model.safetensors",
|
| 658 |
+
"model.layers.34.mlp.down_proj.scales": "model.safetensors",
|
| 659 |
+
"model.layers.34.mlp.down_proj.weight": "model.safetensors",
|
| 660 |
+
"model.layers.34.mlp.gate_proj.biases": "model.safetensors",
|
| 661 |
+
"model.layers.34.mlp.gate_proj.scales": "model.safetensors",
|
| 662 |
+
"model.layers.34.mlp.gate_proj.weight": "model.safetensors",
|
| 663 |
+
"model.layers.34.mlp.up_proj.biases": "model.safetensors",
|
| 664 |
+
"model.layers.34.mlp.up_proj.scales": "model.safetensors",
|
| 665 |
+
"model.layers.34.mlp.up_proj.weight": "model.safetensors",
|
| 666 |
+
"model.layers.34.post_attention_layernorm.weight": "model.safetensors",
|
| 667 |
+
"model.layers.34.self_attn.k_proj.biases": "model.safetensors",
|
| 668 |
+
"model.layers.34.self_attn.k_proj.scales": "model.safetensors",
|
| 669 |
+
"model.layers.34.self_attn.k_proj.weight": "model.safetensors",
|
| 670 |
+
"model.layers.34.self_attn.o_proj.biases": "model.safetensors",
|
| 671 |
+
"model.layers.34.self_attn.o_proj.scales": "model.safetensors",
|
| 672 |
+
"model.layers.34.self_attn.o_proj.weight": "model.safetensors",
|
| 673 |
+
"model.layers.34.self_attn.q_proj.biases": "model.safetensors",
|
| 674 |
+
"model.layers.34.self_attn.q_proj.scales": "model.safetensors",
|
| 675 |
+
"model.layers.34.self_attn.q_proj.weight": "model.safetensors",
|
| 676 |
+
"model.layers.34.self_attn.v_proj.biases": "model.safetensors",
|
| 677 |
+
"model.layers.34.self_attn.v_proj.scales": "model.safetensors",
|
| 678 |
+
"model.layers.34.self_attn.v_proj.weight": "model.safetensors",
|
| 679 |
+
"model.layers.35.input_layernorm.weight": "model.safetensors",
|
| 680 |
+
"model.layers.35.mlp.down_proj.biases": "model.safetensors",
|
| 681 |
+
"model.layers.35.mlp.down_proj.scales": "model.safetensors",
|
| 682 |
+
"model.layers.35.mlp.down_proj.weight": "model.safetensors",
|
| 683 |
+
"model.layers.35.mlp.gate_proj.biases": "model.safetensors",
|
| 684 |
+
"model.layers.35.mlp.gate_proj.scales": "model.safetensors",
|
| 685 |
+
"model.layers.35.mlp.gate_proj.weight": "model.safetensors",
|
| 686 |
+
"model.layers.35.mlp.up_proj.biases": "model.safetensors",
|
| 687 |
+
"model.layers.35.mlp.up_proj.scales": "model.safetensors",
|
| 688 |
+
"model.layers.35.mlp.up_proj.weight": "model.safetensors",
|
| 689 |
+
"model.layers.35.post_attention_layernorm.weight": "model.safetensors",
|
| 690 |
+
"model.layers.35.self_attn.k_proj.biases": "model.safetensors",
|
| 691 |
+
"model.layers.35.self_attn.k_proj.scales": "model.safetensors",
|
| 692 |
+
"model.layers.35.self_attn.k_proj.weight": "model.safetensors",
|
| 693 |
+
"model.layers.35.self_attn.o_proj.biases": "model.safetensors",
|
| 694 |
+
"model.layers.35.self_attn.o_proj.scales": "model.safetensors",
|
| 695 |
+
"model.layers.35.self_attn.o_proj.weight": "model.safetensors",
|
| 696 |
+
"model.layers.35.self_attn.q_proj.biases": "model.safetensors",
|
| 697 |
+
"model.layers.35.self_attn.q_proj.scales": "model.safetensors",
|
| 698 |
+
"model.layers.35.self_attn.q_proj.weight": "model.safetensors",
|
| 699 |
+
"model.layers.35.self_attn.v_proj.biases": "model.safetensors",
|
| 700 |
+
"model.layers.35.self_attn.v_proj.scales": "model.safetensors",
|
| 701 |
+
"model.layers.35.self_attn.v_proj.weight": "model.safetensors",
|
| 702 |
+
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
| 703 |
+
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
| 704 |
+
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
| 705 |
+
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
| 706 |
+
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
| 707 |
+
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
| 708 |
+
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
| 709 |
+
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
| 710 |
+
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
| 711 |
+
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 712 |
+
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 713 |
+
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
| 714 |
+
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
| 715 |
+
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 716 |
+
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
| 717 |
+
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
| 718 |
+
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
| 719 |
+
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
| 720 |
+
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
| 721 |
+
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 722 |
+
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
| 723 |
+
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
| 724 |
+
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 725 |
+
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
| 726 |
+
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
| 727 |
+
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
| 728 |
+
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
| 729 |
+
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
| 730 |
+
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
| 731 |
+
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
| 732 |
+
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
| 733 |
+
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
| 734 |
+
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 735 |
+
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 736 |
+
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
| 737 |
+
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 738 |
+
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 739 |
+
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
| 740 |
+
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
| 741 |
+
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
| 742 |
+
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
| 743 |
+
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 744 |
+
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 745 |
+
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
| 746 |
+
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 747 |
+
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 748 |
+
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
| 749 |
+
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
| 750 |
+
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
| 751 |
+
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
| 752 |
+
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
| 753 |
+
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
| 754 |
+
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
| 755 |
+
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
| 756 |
+
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
| 757 |
+
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 758 |
+
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 759 |
+
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
| 760 |
+
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
| 761 |
+
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 762 |
+
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
| 763 |
+
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
| 764 |
+
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
| 765 |
+
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
| 766 |
+
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
| 767 |
+
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 768 |
+
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
| 769 |
+
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
| 770 |
+
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 771 |
+
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
| 772 |
+
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
| 773 |
+
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
| 774 |
+
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
| 775 |
+
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
| 776 |
+
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
| 777 |
+
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
| 778 |
+
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
| 779 |
+
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
| 780 |
+
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 781 |
+
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 782 |
+
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
| 783 |
+
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
| 784 |
+
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 785 |
+
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
| 786 |
+
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
| 787 |
+
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
| 788 |
+
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
| 789 |
+
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
| 790 |
+
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 791 |
+
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
| 792 |
+
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
| 793 |
+
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 794 |
+
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
| 795 |
+
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
| 796 |
+
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
| 797 |
+
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
| 798 |
+
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
| 799 |
+
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
| 800 |
+
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
| 801 |
+
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
| 802 |
+
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
| 803 |
+
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 804 |
+
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 805 |
+
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
| 806 |
+
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 807 |
+
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 808 |
+
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
| 809 |
+
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
| 810 |
+
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
| 811 |
+
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
| 812 |
+
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 813 |
+
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 814 |
+
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
| 815 |
+
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 816 |
+
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 817 |
+
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
| 818 |
+
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
| 819 |
+
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
| 820 |
+
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
| 821 |
+
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
| 822 |
+
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
| 823 |
+
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
| 824 |
+
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
| 825 |
+
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
| 826 |
+
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
| 827 |
+
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 828 |
+
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
| 829 |
+
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
| 830 |
+
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 831 |
+
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
| 832 |
+
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
| 833 |
+
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
| 834 |
+
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
| 835 |
+
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
| 836 |
+
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 837 |
+
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
| 838 |
+
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
| 839 |
+
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 840 |
+
"model.norm.weight": "model.safetensors"
|
| 841 |
+
}
|
| 842 |
+
}
|