初始化项目，由ModelHub XC社区提供模型
Model: kakaocorp/kanana-1.5-8b-instruct-2505 Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
194
LICENSE
Normal file
194
LICENSE
Normal file
@@ -0,0 +1,194 @@
|
||||
Apache License
|
||||
==============
|
||||
|
||||
_Version 2.0, January 2004_
|
||||
_<<http://www.apache.org/licenses/>>_
|
||||
|
||||
### Terms and Conditions for use, reproduction, and distribution
|
||||
|
||||
#### 1. Definitions
|
||||
|
||||
“License” shall mean the terms and conditions for use, reproduction, and
|
||||
distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
“Licensor” shall mean the copyright owner or entity authorized by the copyright
|
||||
owner that is granting the License.
|
||||
|
||||
“Legal Entity” shall mean the union of the acting entity and all other entities
|
||||
that control, are controlled by, or are under common control with that entity.
|
||||
For the purposes of this definition, “control” means **(i)** the power, direct or
|
||||
indirect, to cause the direction or management of such entity, whether by
|
||||
contract or otherwise, or **(ii)** ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or **(iii)** beneficial ownership of such entity.
|
||||
|
||||
“You” (or “Your”) shall mean an individual or Legal Entity exercising
|
||||
permissions granted by this License.
|
||||
|
||||
“Source” form shall mean the preferred form for making modifications, including
|
||||
but not limited to software source code, documentation source, and configuration
|
||||
files.
|
||||
|
||||
“Object” form shall mean any form resulting from mechanical transformation or
|
||||
translation of a Source form, including but not limited to compiled object code,
|
||||
generated documentation, and conversions to other media types.
|
||||
|
||||
“Work” shall mean the work of authorship, whether in Source or Object form, made
|
||||
available under the License, as indicated by a copyright notice that is included
|
||||
in or attached to the work (an example is provided in the Appendix below).
|
||||
|
||||
“Derivative Works” shall mean any work, whether in Source or Object form, that
|
||||
is based on (or derived from) the Work and for which the editorial revisions,
|
||||
annotations, elaborations, or other modifications represent, as a whole, an
|
||||
original work of authorship. For the purposes of this License, Derivative Works
|
||||
shall not include works that remain separable from, or merely link (or bind by
|
||||
name) to the interfaces of, the Work and Derivative Works thereof.
|
||||
|
||||
“Contribution” shall mean any work of authorship, including the original version
|
||||
of the Work and any modifications or additions to that Work or Derivative Works
|
||||
thereof, that is intentionally submitted to Licensor for inclusion in the Work
|
||||
by the copyright owner or by an individual or Legal Entity authorized to submit
|
||||
on behalf of the copyright owner. For the purposes of this definition,
|
||||
“submitted” means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems, and
|
||||
issue tracking systems that are managed by, or on behalf of, the Licensor for
|
||||
the purpose of discussing and improving the Work, but excluding communication
|
||||
that is conspicuously marked or otherwise designated in writing by the copyright
|
||||
owner as “Not a Contribution.”
|
||||
|
||||
“Contributor” shall mean Licensor and any individual or Legal Entity on behalf
|
||||
of whom a Contribution has been received by Licensor and subsequently
|
||||
incorporated within the Work.
|
||||
|
||||
#### 2. Grant of Copyright License
|
||||
|
||||
Subject to the terms and conditions of this License, each Contributor hereby
|
||||
grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free,
|
||||
irrevocable copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the Work and such
|
||||
Derivative Works in Source or Object form.
|
||||
|
||||
#### 3. Grant of Patent License
|
||||
|
||||
Subject to the terms and conditions of this License, each Contributor hereby
|
||||
grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free,
|
||||
irrevocable (except as stated in this section) patent license to make, have
|
||||
made, use, offer to sell, sell, import, and otherwise transfer the Work, where
|
||||
such license applies only to those patent claims licensable by such Contributor
|
||||
that are necessarily infringed by their Contribution(s) alone or by combination
|
||||
of their Contribution(s) with the Work to which such Contribution(s) was
|
||||
submitted. If You institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work or a
|
||||
Contribution incorporated within the Work constitutes direct or contributory
|
||||
patent infringement, then any patent licenses granted to You under this License
|
||||
for that Work shall terminate as of the date such litigation is filed.
|
||||
|
||||
#### 4. Redistribution
|
||||
|
||||
You may reproduce and distribute copies of the Work or Derivative Works thereof
|
||||
in any medium, with or without modifications, and in Source or Object form,
|
||||
provided that You meet the following conditions:
|
||||
|
||||
* **(a)** You must give any other recipients of the Work or Derivative Works a copy of
|
||||
this License; and
|
||||
* **(b)** You must cause any modified files to carry prominent notices stating that You
|
||||
changed the files; and
|
||||
* **(c)** You must retain, in the Source form of any Derivative Works that You distribute,
|
||||
all copyright, patent, trademark, and attribution notices from the Source form
|
||||
of the Work, excluding those notices that do not pertain to any part of the
|
||||
Derivative Works; and
|
||||
* **(d)** If the Work includes a “NOTICE” text file as part of its distribution, then any
|
||||
Derivative Works that You distribute must include a readable copy of the
|
||||
attribution notices contained within such NOTICE file, excluding those notices
|
||||
that do not pertain to any part of the Derivative Works, in at least one of the
|
||||
following places: within a NOTICE text file distributed as part of the
|
||||
Derivative Works; within the Source form or documentation, if provided along
|
||||
with the Derivative Works; or, within a display generated by the Derivative
|
||||
Works, if and wherever such third-party notices normally appear. The contents of
|
||||
the NOTICE file are for informational purposes only and do not modify the
|
||||
License. You may add Your own attribution notices within Derivative Works that
|
||||
You distribute, alongside or as an addendum to the NOTICE text from the Work,
|
||||
provided that such additional attribution notices cannot be construed as
|
||||
modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and may provide
|
||||
additional or different license terms and conditions for use, reproduction, or
|
||||
distribution of Your modifications, or for any such Derivative Works as a whole,
|
||||
provided Your use, reproduction, and distribution of the Work otherwise complies
|
||||
with the conditions stated in this License.
|
||||
|
||||
#### 5. Submission of Contributions
|
||||
|
||||
Unless You explicitly state otherwise, any Contribution intentionally submitted
|
||||
for inclusion in the Work by You to the Licensor shall be under the terms and
|
||||
conditions of this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify the terms of
|
||||
any separate license agreement you may have executed with Licensor regarding
|
||||
such Contributions.
|
||||
|
||||
#### 6. Trademarks
|
||||
|
||||
This License does not grant permission to use the trade names, trademarks,
|
||||
service marks, or product names of the Licensor, except as required for
|
||||
reasonable and customary use in describing the origin of the Work and
|
||||
reproducing the content of the NOTICE file.
|
||||
|
||||
#### 7. Disclaimer of Warranty
|
||||
|
||||
Unless required by applicable law or agreed to in writing, Licensor provides the
|
||||
Work (and each Contributor provides its Contributions) on an “AS IS” BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied,
|
||||
including, without limitation, any warranties or conditions of TITLE,
|
||||
NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are
|
||||
solely responsible for determining the appropriateness of using or
|
||||
redistributing the Work and assume any risks associated with Your exercise of
|
||||
permissions under this License.
|
||||
|
||||
#### 8. Limitation of Liability
|
||||
|
||||
In no event and under no legal theory, whether in tort (including negligence),
|
||||
contract, or otherwise, unless required by applicable law (such as deliberate
|
||||
and grossly negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special, incidental,
|
||||
or consequential damages of any character arising as a result of this License or
|
||||
out of the use or inability to use the Work (including but not limited to
|
||||
damages for loss of goodwill, work stoppage, computer failure or malfunction, or
|
||||
any and all other commercial damages or losses), even if such Contributor has
|
||||
been advised of the possibility of such damages.
|
||||
|
||||
#### 9. Accepting Warranty or Additional Liability
|
||||
|
||||
While redistributing the Work or Derivative Works thereof, You may choose to
|
||||
offer, and charge a fee for, acceptance of support, warranty, indemnity, or
|
||||
other liability obligations and/or rights consistent with this License. However,
|
||||
in accepting such obligations, You may act only on Your own behalf and on Your
|
||||
sole responsibility, not on behalf of any other Contributor, and only if You
|
||||
agree to indemnify, defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason of your
|
||||
accepting any such warranty or additional liability.
|
||||
|
||||
_END OF TERMS AND CONDITIONS_
|
||||
|
||||
### APPENDIX: How to apply the Apache License to your work
|
||||
|
||||
To apply the Apache License to your work, attach the following boilerplate
|
||||
notice, with the fields enclosed by brackets `[]` replaced with your own
|
||||
identifying information. (Don't include the brackets!) The text should be
|
||||
enclosed in the appropriate comment syntax for the file format. We also
|
||||
recommend that a file or class name and description of purpose be included on
|
||||
the same “printed page” as the copyright notice for easier identification within
|
||||
third-party archives.
|
||||
|
||||
Copyright [yyyy] [name of copyright owner]
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
188
README.md
Normal file
188
README.md
Normal file
@@ -0,0 +1,188 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
- ko
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
pipeline_tag: text-generation
|
||||
model_id: kakaocorp/kanana-1.5-8b-instruct-2505
|
||||
repo: kakaocorp/kanana-1.5-8b-instruct-2505
|
||||
developers: Kanana LLM
|
||||
training_regime: bf16 mixed precision
|
||||
---
|
||||
|
||||
<p align="center">
|
||||
<br>
|
||||
<picture>
|
||||
<img src="./assets/logo/kanana-logo.png" width="60%" style="margin: 40px auto;">
|
||||
</picture>
|
||||
</br>
|
||||
|
||||
<p align="center">
|
||||
🤗 <a href="https://kko.kakao.com/kananallm">1.5 HF Models</a>   |
|
||||
  📕 <a href="https://tech.kakao.com/posts/707">1.5 Blog</a>   |
|
||||
  📜 <a href="https://arxiv.org/abs/2502.18934">Technical Report</a>
|
||||
|
||||
|
||||
<br>
|
||||
|
||||
## News 🔥
|
||||
|
||||
- ✨`2025/05/23`: Published a [blog post](https://tech.kakao.com/posts/707) about `Kanana 1.5` models and released 🤗[HF model weights](https://kko.kakao.com/kananallm).
|
||||
- 📜`2025/02/27`: Released [Technical Report](https://arxiv.org/abs/2502.18934) and 🤗[HF model weights](https://huggingface.co/collections/kakaocorp/kanana-nano-21b-67a326cda1c449c8d4172259).
|
||||
- 📕`2025/01/10`: Published a [blog post](https://tech.kakao.com/posts/682) about the development of `Kanana Nano` model.
|
||||
- 📕`2024/11/14`: Published blog posts ([pre-training](https://tech.kakao.com/posts/661), [post-training](https://tech.kakao.com/posts/662)) about the development of `Kanana` models.
|
||||
- ▶️`2024/11/06`: Published a [presentation video](https://youtu.be/HTBl142x9GI?si=o_we6t9suYK8DfX3) about the development of the `Kanana` models.
|
||||
|
||||
<br>
|
||||
|
||||
## Table of Contents
|
||||
|
||||
- [Kanana 1.5](#kanana-15)
|
||||
- [Performance](#performance)
|
||||
- [Base Model Evaluation](#base-model-evaluation)
|
||||
- [Instruct Model Evaluation](#instruct-model-evaluation)
|
||||
- [Processing 32K+ Length](#processing-32k-length)
|
||||
- [Contributors](#contributors)
|
||||
- [Citation](#citation)
|
||||
- [Contact](#contact)
|
||||
|
||||
<br>
|
||||
|
||||
# Kanana 1.5
|
||||
|
||||
`Kanana 1.5`, a newly introduced version of the Kanana model family, presents substantial enhancements in **coding, mathematics, and function calling capabilities** over the previous version, enabling broader application to more complex real-world problems. This new version now can handle __up to 32K tokens length natively and up to 128K tokens using YaRN__, allowing the model to maintain coherence when handling extensive documents or engaging in extended conversations. Furthermore, Kanana 1.5 delivers more natural and accurate conversations through a __refined post-training process__.
|
||||
|
||||
<p align="center">
|
||||
<br>
|
||||
<picture>
|
||||
<img src="./assets/performance/kanana-1.5-radar-8b.png" width="95%" style="margin: 40px auto;">
|
||||
</picture>
|
||||
</br>
|
||||
|
||||
> [!Note]
|
||||
> Neither the pre-training nor the post-training data includes Kakao user data.
|
||||
|
||||
## Performance
|
||||
|
||||
### Base Model Evaluation
|
||||
<table>
|
||||
<tr>
|
||||
<th>Models</th>
|
||||
<th>MMLU</th>
|
||||
<th>KMMLU</th>
|
||||
<th>HAERAE</th>
|
||||
<th>HumanEval</th>
|
||||
<th>MBPP</th>
|
||||
<th>GSM8K</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Kanana-1.5-8B</td>
|
||||
<td align="center">64.24</td>
|
||||
<td align="center">48.94</td>
|
||||
<td align="center">82.77</td>
|
||||
<td align="center">61.59</td>
|
||||
<td align="center">57.80</td>
|
||||
<td align="center">63.53</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Kanana-8B</td>
|
||||
<td align="center">64.22</td>
|
||||
<td align="center">48.30</td>
|
||||
<td align="center">83.41</td>
|
||||
<td align="center">40.24</td>
|
||||
<td align="center">51.40</td>
|
||||
<td align="center">57.09</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
<br>
|
||||
|
||||
### Instruct Model Evaluation
|
||||
<table>
|
||||
<tr>
|
||||
<th>Models</th>
|
||||
<th>MT-Bench</th>
|
||||
<th>KoMT-Bench</th>
|
||||
<th>IFEval</th>
|
||||
<th>HumanEval+</th>
|
||||
<th>MBPP+</th>
|
||||
<th>GSM8K (0-shot)</th>
|
||||
<th>MATH</th>
|
||||
<th>MMLU (0-shot, CoT)</th>
|
||||
<th>KMMLU (0-shot, CoT)</th>
|
||||
<th>FunctionChatBench</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><strong>Kanana-1.5-8B*</strong></td>
|
||||
<td align="center">7.76</td>
|
||||
<td align="center">7.63</td>
|
||||
<td align="center">80.11</td>
|
||||
<td align="center">76.83</td>
|
||||
<td align="center">67.99</td>
|
||||
<td align="center">87.64</td>
|
||||
<td align="center">67.54</td>
|
||||
<td align="center">68.82</td>
|
||||
<td align="center">48.28</td>
|
||||
<td align="center">58.00</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Kanana-8B</td>
|
||||
<td align="center">7.13</td>
|
||||
<td align="center">6.92</td>
|
||||
<td align="center">76.91</td>
|
||||
<td align="center">62.20</td>
|
||||
<td align="center">43.92</td>
|
||||
<td align="center">79.23</td>
|
||||
<td align="center">37.68</td>
|
||||
<td align="center">66.50</td>
|
||||
<td align="center">47.43</td>
|
||||
<td align="center">17.37</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
> [!Note]
|
||||
> \* Models released under Apache 2.0 are trained on the latest versions compared to other models.
|
||||
|
||||
<br>
|
||||
|
||||
## Processing 32K+ Length
|
||||
Currently, the `config.json` uploaded to HuggingFace is configured for token lengths of 32,768 or less. To process tokens beyond this length, YaRN must be applied. By updating the `config.json` with the following parameters, you can apply YaRN to handle token sequences up to 128K in length:
|
||||
```json
|
||||
"rope_scaling": {
|
||||
"factor": 4.4,
|
||||
"original_max_position_embeddings": 32768,
|
||||
"type": "yarn",
|
||||
"beta_fast": 64,
|
||||
"beta_slow": 2
|
||||
},
|
||||
```
|
||||
|
||||
<br>
|
||||
|
||||
## Contributors
|
||||
- Language Model Training: Yunju Bak, Doohae Jung, Boseop Kim, Nayeon Kim, Hojin Lee, Jaesun Park, Minho Ryu
|
||||
- Language Model Alignment: Jiyeon Ham, Seungjae Jung, Hyunho Kim, Hyunwoong Ko, Changmin Lee, Daniel Wontae Nam
|
||||
- AI Engineering: Youmin Kim, Hyeongju Kim
|
||||
|
||||
<br>
|
||||
|
||||
## Citation
|
||||
|
||||
```
|
||||
@misc{kananallmteam2025kananacomputeefficientbilinguallanguage,
|
||||
title={Kanana: Compute-efficient Bilingual Language Models},
|
||||
author={Kanana LLM Team and Yunju Bak and Hojin Lee and Minho Ryu and Jiyeon Ham and Seungjae Jung and Daniel Wontae Nam and Taegyeong Eo and Donghun Lee and Doohae Jung and Boseop Kim and Nayeon Kim and Jaesun Park and Hyunho Kim and Hyunwoong Ko and Changmin Lee and Kyoung-Woon On and Seulye Baeg and Junrae Cho and Sunghee Jung and Jieun Kang and EungGyun Kim and Eunhwa Kim and Byeongil Ko and Daniel Lee and Minchul Lee and Miok Lee and Shinbok Lee and Gaeun Seo},
|
||||
year={2025},
|
||||
eprint={2502.18934},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL},
|
||||
url={https://arxiv.org/abs/2502.18934},
|
||||
}
|
||||
```
|
||||
|
||||
<br>
|
||||
|
||||
## Contact
|
||||
- Kanana LLM Team Technical Support: kanana-llm@kakaocorp.com
|
||||
- Business & Partnership Contact: alpha.k@kakaocorp.com
|
||||
BIN
assets/logo/kanana-logo.png
Normal file
BIN
assets/logo/kanana-logo.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 58 KiB |
BIN
assets/performance/kanana-1.5-radar-8b.png
Normal file
BIN
assets/performance/kanana-1.5-radar-8b.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 839 KiB |
BIN
assets/performance/kanana-1.5-radar.png
Normal file
BIN
assets/performance/kanana-1.5-radar.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 842 KiB |
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128009,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 128001,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 8000000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.48.3",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128259
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128009,
|
||||
"pad_token_id": 128001,
|
||||
"transformers_version": "4.48.3"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:636be023406874bc59c62167c4d3b93ffe761a4c454f2062f0f8adb627d767aa
|
||||
size 4932701536
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a45e6a3b5faa72d4f03ba65735e5b924bd832e211d13de13475e8a5c0c0ac593
|
||||
size 4901217648
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:242db2de2a9afea6d5848f4477a4eca067aae352f239907d1f1ec73bcf68904d
|
||||
size 4901225464
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f936ffa1c2fa3918c3ce1233628453c24f2c8d53fb41aaf3b657a1e66f978150
|
||||
size 1325460880
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16060571648
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00001-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:31d17e500c82ff116fc14d4dd0106a08e49bd3512d8a81473047121ef8ea09f9
|
||||
size 17210524
|
||||
2088
tokenizer_config.json
Normal file
2088
tokenizer_config.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user