tokyotech-llm/Swallow-7b-instruct-v0.1
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: tokyotech-llm/Swallow-7b-instruct-v0.1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-03 07:36:14 +08:00
commit b5d9bd92f9
16 changed files with 874 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
.gitattributes vendored Normal file
View File

@@ -0,0 +1,53 @@
*.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
*.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
*.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
model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
tokenizer.model filter=lfs diff=lfs merge=lfs -text
model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
logo.png filter=lfs diff=lfs merge=lfs -text

128
LICENSE.txt Normal file
View File

@@ -0,0 +1,128 @@
LLAMA 2 COMMUNITY LICENSE AGREEMENT
Llama 2 Version Release Date: July 18, 2023
"Agreement" means the terms and conditions for use, reproduction, distribution and
modification of the Llama Materials set forth herein.
"Documentation" means the specifications, manuals and documentation
accompanying Llama 2 distributed by Meta at ai.meta.com/resources/models-and-
libraries/llama-downloads/.
"Licensee" or "you" means you, or your employer or any other person or entity (if
you are entering into this Agreement on such person or entity's behalf), of the age
required under applicable laws, rules or regulations to provide legal consent and that
has legal authority to bind your employer or such other person or entity if you are
entering in this Agreement on their behalf.
"Llama 2" means the foundational large language models and software and
algorithms, including machine-learning model code, trained model weights,
inference-enabling code, training-enabling code, fine-tuning enabling code and other
elements of the foregoing distributed by Meta at ai.meta.com/resources/models-and-
libraries/llama-downloads/.
"Llama Materials" means, collectively, Meta's proprietary Llama 2 and
Documentation (and any portion thereof) made available under this Agreement.
"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you
are an entity, your principal place of business is in the EEA or Switzerland) and Meta
Platforms, Inc. (if you are located outside of the EEA or Switzerland).
By clicking "I Accept" below or by using or distributing any portion or element of the
Llama Materials, you agree to be bound by this Agreement.
1. License Rights and Redistribution.
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-
transferable and royalty-free limited license under Meta's intellectual property or
other rights owned by Meta embodied in the Llama Materials to use, reproduce,
distribute, copy, create derivative works of, and make modifications to the Llama
Materials.
b. Redistribution and Use.
i. If you distribute or make the Llama Materials, or any derivative works
thereof, available to a third party, you shall provide a copy of this Agreement to such
third party.
ii. If you receive Llama Materials, or any derivative works thereof, from
a Licensee as part of an integrated end user product, then Section 2 of this
Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you
distribute the following attribution notice within a "Notice" text file distributed as a
part of such copies: "Llama 2 is licensed under the LLAMA 2 Community License,
Copyright (c) Meta Platforms, Inc. All Rights Reserved."
iv. Your use of the Llama Materials must comply with applicable laws
and regulations (including trade compliance laws and regulations) and adhere to the
Acceptable Use Policy for the Llama Materials (available at
https://ai.meta.com/llama/use-policy), which is hereby incorporated by reference into
this Agreement.
v. You will not use the Llama Materials or any output or results of the
Llama Materials to improve any other large language model (excluding Llama 2 or
derivative works thereof).
2. Additional Commercial Terms. If, on the Llama 2 version release date, the
monthly active users of the products or services made available by or for Licensee,
or Licensee's affiliates, is greater than 700 million monthly active users in the
preceding calendar month, you must request a license from Meta, which Meta may
grant to you in its sole discretion, and you are not authorized to exercise any of the
rights under this Agreement unless or until Meta otherwise expressly grants you
such rights.
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE
LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE
PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY
WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR
FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING
THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR
USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE
LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT,
NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS
AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL,
CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN
IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF
ANY OF THE FOREGOING.
5. Intellectual Property.
a. No trademark licenses are granted under this Agreement, and in
connection with the Llama Materials, neither Meta nor Licensee may use any name
or mark owned by or associated with the other or any of its affiliates, except as
required for reasonable and customary use in describing and redistributing the
Llama Materials.
b. Subject to Meta's ownership of Llama Materials and derivatives made by or
for Meta, with respect to any derivative works and modifications of the Llama
Materials that are made by you, as between you and Meta, you are and will be the
owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity
(including a cross-claim or counterclaim in a lawsuit) alleging that the Llama
Materials or Llama 2 outputs or results, or any portion of any of the foregoing,
constitutes infringement of intellectual property or other rights owned or licensable
by you, then any licenses granted to you under this Agreement shall terminate as of
the date such litigation or claim is filed or instituted. You will indemnify and hold
harmless Meta from and against any claim by any third party arising out of or related
to your use or distribution of the Llama Materials.
6. Term and Termination. The term of this Agreement will commence upon your
acceptance of this Agreement or access to the Llama Materials and will continue in
full force and effect until terminated in accordance with the terms and conditions
herein. Meta may terminate this Agreement if you are in breach of any term or
condition of this Agreement. Upon termination of this Agreement, you shall delete
and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the
termination of this Agreement.
7. Governing Law and Jurisdiction. This Agreement will be governed and
construed under the laws of the State of California without regard to choice of law
principles, and the UN Convention on Contracts for the International Sale of Goods
does not apply to this Agreement. The courts of California shall have exclusive
jurisdiction of any dispute arising out of this Agreement.

1
Notice Normal file
View File

@@ -0,0 +1 @@
Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.

272
README.md Normal file
View File

@@ -0,0 +1,272 @@
---
language:
- en
- ja
library_name: transformers
pipeline_tag: text-generation
license: llama2
model_type: llama
---
# Swallow
Our Swallow model has undergone continual pre-training from the [Llama 2 family](https://huggingface.co/meta-llama), primarily with the addition of Japanese language data. The tuned versions use supervised fine-tuning (SFT).
Links to other models can be found in the index.
# Model Release Updates
We are excited to share the release schedule for our latest models:
- **April 26, 2024**: Released version 0.1 of our enhanced instruction-tuned models: [Swallow-7b-instruct-v0.1](https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-v0.1), [Swallow-13b-instruct-v0.1](https://huggingface.co/tokyotech-llm/Swallow-13b-instruct-v0.1), and [Swallow-70b-instruct-v0.1](https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-v0.1) as preview versions.
- **March 2, 2024**: Released the [Swallow-7b-plus-hf](https://huggingface.co/tokyotech-llm/Swallow-7b-plus-hf), a model trained with approximately twice as many Japanese tokens as [Swallow-7b-hf](https://huggingface.co/tokyotech-llm/Swallow-7b-hf).
- **February 4, 2024**: Released the [Swallow-13b-NVE-hf](https://huggingface.co/tokyotech-llm/Swallow-13b-NVE-hf).
- **January 26, 2024**: Released the [Swallow-7b-NVE-hf](https://huggingface.co/tokyotech-llm/Swallow-7b-NVE-hf), [Swallow-7b-NVE-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-7b-NVE-instruct-hf), [Swallow-70b-NVE-hf](https://huggingface.co/tokyotech-llm/Swallow-70b-NVE-hf), and [Swallow-70b-NVE-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-70b-NVE-instruct-hf)
- **December 19, 2023**: Released the [Swallow-7b-hf](https://huggingface.co/tokyotech-llm/Swallow-7b-hf), [Swallow-7b-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-hf), [Swallow-13b-hf](https://huggingface.co/tokyotech-llm/Swallow-13b-hf), [Swallow-13b-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-13b-instruct-hf), [Swallow-70b-hf](https://huggingface.co/tokyotech-llm/Swallow-70b-hf), and [Swallow-70b-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-hf).
## Swallow Model Index
|Model|Swallow-hf|Swallow-instruct-hf|Swallow-instruct-v0.1|
|---|---|---|---|
|7B| [Link](https://huggingface.co/tokyotech-llm/Swallow-7b-hf) | [Link](https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-hf)|[Link](https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-v1.0)|
|7B-Plus| [Link](https://huggingface.co/tokyotech-llm/Swallow-7b-plus-hf) | N/A | N/A |
|13B| [Link](https://huggingface.co/tokyotech-llm/Swallow-13b-hf) | [Link](https://huggingface.co/tokyotech-llm/Swallow-13b-instruct-hf)| [Link](https://huggingface.co/tokyotech-llm/Swallow-13b-instruct-v1.0)|
|70B| [Link](https://huggingface.co/tokyotech-llm/Swallow-70b-hf) | [Link](https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-hf)| [Link](https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-v1.0)|
## Swallow Model Index NVE (No Vocabulary Expansion)
|Model|Swallow-NVE-hf|Swallow-NVE-instruct-hf|
|---|---|---|
|7B| [Link](https://huggingface.co/tokyotech-llm/Swallow-7b-NVE-hf) | [Link](https://huggingface.co/tokyotech-llm/Swallow-7b-NVE-instruct-hf)|
|13B| [Link](https://huggingface.co/tokyotech-llm/Swallow-13b-NVE-hf) | N/A |
|70B| [Link](https://huggingface.co/tokyotech-llm/Swallow-70b-NVE-hf) | [Link](https://huggingface.co/tokyotech-llm/Swallow-70b-NVE-instruct-hf)|
![logo](./logo.png)
This repository provides large language models developed by [TokyoTech-LLM](https://tokyotech-llm.github.io/).
## Model Details
* **Model type**: Please refer to LLaMA-2 technical report for details on the model architecture.
* **Language(s)**: Japanese English
* **Tokenizer**: This model employs a tokenizer that features a broadened vocabulary based on Japanese data. This allows for a more efficient representation of text using fewer tokens, leading to a notably faster inference process.
* **Contact**: swallow[at]nlp.c.titech.ac.jp
## Instruct Model Performance
### MT-Bench JA
#### Comparison to the past version
* NOTE that the models with the `v0.1` suffix are newer versions compared to their original counterparts with the `hf`.
* We report overall (i.e., average over scores of the first and second turns), first, and second turn scores.
##### Overall
|Model|Average|Writing|Roleplay|Reasoning|Math|Coding|Extraction|STEM|Humanities|
|---|---|---|---|---|---|---|---|---|---|
| Swallow-7b-instruct-v0.1 |0.3435|0.4450|0.4720|0.1853|0.1920|0.2204|0.3015|0.4594|0.4720|
| Swallow-7b-instruct-hf |0.1833|0.2205|0.1975|0.1593|0.1045|0.1282|0.2672|0.1908|0.1980|
| Swallow-13b-instruct-v0.1 |0.3669|0.4816|0.5562|0.2769|0.1020|0.1505|0.4179|0.4347|0.5150|
| Swallow-13b-instruct-hf |0.2004|0.1932|0.2552|0.1507|0.1184|0.1285|0.2641|0.2434|0.2500|
| Swallow-70b-instruct-v0.1 |0.4513|0.4822|0.5353|0.3497|0.3492|0.2668|0.5553|0.4955|0.5767|
| Swallow-70b-instruct-hf |0.3259|0.2925|0.4283|0.3447|0.1562|0.1856|0.5634|0.3315|0.3071|
##### First Turn
|Model|Average|Writing|Roleplay|Reasoning|Math|Coding|Extraction|STEM|Humanities|
|---|---|---|---|---|---|---|---|---|---|
| Swallow-7b-instruct-v0.1 |0.3829|0.4960|0.4800|0.2220|0.2820|0.2164|0.3220|0.5440|0.4980|
| Swallow-7b-instruct-hf |0.2216|0.2830|0.2150|0.1590|0.1080|0.1470|0.3542|0.2450|0.2650|
| Swallow-13b-instruct-v0.1 |0.3948|0.5400|0.5220|0.3020|0.1040|0.1760|0.5040|0.5180|0.4920|
| Swallow-13b-instruct-hf |0.2304|0.2460|0.2640|0.1610|0.1360|0.1330|0.3070|0.3010|0.2950|
| Swallow-70b-instruct-v0.1 |0.4849|0.5720|0.5020|0.4780|0.3680|0.2467|0.5400|0.5720|0.5960|
| Swallow-70b-instruct-hf |0.3631|0.3420|0.4007|0.4220|0.1580|0.2044|0.6120|0.4280|0.3360|
##### Second Turn
|Model|Average|Writing|Roleplay|Reasoning|Math|Coding|Extraction|STEM|Humanities|
|---|---|---|---|---|---|---|---|---|---|
| Swallow-7b-instruct-v0.1 |0.3059|0.3940|0.4640|0.1441|0.1000|0.2253|0.2811|0.3724|0.4449|
| Swallow-7b-instruct-hf |0.1432|0.1567|0.1798|0.1603|0.1010|0.1085|0.1767|0.1343|0.1295|
| Swallow-13b-instruct-v0.1 |0.3353|0.4213|0.5911|0.2516|0.1000|0.1244|0.3194|0.3473|0.5394|
| Swallow-13b-instruct-hf |0.1692|0.1364|0.2453|0.1401|0.1000|0.1237|0.2199|0.1850|0.2050|
| Swallow-70b-instruct-v0.1 |0.4179|0.3913|0.5689|0.2184|0.3280|0.2884|0.5711|0.4171|0.5562|
| Swallow-70b-instruct-hf |0.2872|0.2398|0.4564|0.2647|0.1540|0.1676|0.5118|0.2311|0.2762|
#### Comparison to the existing models
We only provide the overall score in this section.
##### 7B models
|Model|Average|Writing|Roleplay|Reasoning|Math|Coding|Extraction|STEM|Humanities|
|---|---|---|---|---|---|---|---|---|---|
| Swallow-7b-instruct-v0.1 |0.3435|0.4450|0.4720|0.1853|0.1920|0.2204|0.3015|0.4594|0.4720|
| ELYZA-japanese-Llama-2-7b-fast-instruct |0.2827|0.3289|0.3907|0.2424|0.1480|0.1584|0.3511|0.3053|0.3365|
| calm2-7b-chat |0.3204|0.4657|0.4898|0.1837|0.1005|0.1414|0.3927|0.3601|0.4293|
| calm2-7b-chat-dpo-experimental |0.3493|0.5312|0.5237|0.1857|0.1000|0.1813|0.3355|0.4320|0.5051|
| RakutenAI-7B-instruct |0.2994|0.3623|0.3711|0.3333|0.1763|0.1581|0.4215|0.2824|0.2901|
| RakutenAI-7B-chat |0.3667|0.4229|0.4644|0.3990|0.2161|0.2390|0.3416|0.3904|0.4601|
##### 13B models
|Model|Average|Writing|Roleplay|Reasoning|Math|Coding|Extraction|STEM|Humanities|
|---|---|---|---|---|---|---|---|---|---|
| Swallow-13b-instruct-v0.1 |0.3669|0.4816|0.5562|0.2769|0.1020|0.1505|0.4179|0.4347|0.5150|
| ELYZA-japanese-Llama-2-13b-instruct |0.3196|0.4400|0.4373|0.2098|0.2157|0.1572|0.3583|0.3243|0.4141|
| ELYZA-japanese-Llama-2-13b-fast-instruct |0.3042|0.3729|0.3930|0.1236|0.2492|0.1862|0.4360|0.3233|0.3496|
##### 70B models
|Model|Average|Writing|Roleplay|Reasoning|Math|Coding|Extraction|STEM|Humanities|
|---|---|---|---|---|---|---|---|---|---|
| Swallow-70b-instruct-v0.1 |0.4513|0.4822|0.5353|0.3497|0.3492|0.2668|0.5553|0.4955|0.5767|
| japanese-stablelm-instruct-beta-70b |0.3716|0.4179|0.3945|0.3656|0.2580|0.2186|0.4412|0.4663|0.4103|
## Evaluation Benchmarks
### MT-Bench JA
We used [Japanese MT-Bench](https://wandb.ai/wandb-japan/llm-leaderboard/artifacts/dataset/mtbench_ja_question) to assess the instruction-following capabilities of models.
We utilized the following settings:
- Implemantation: FastChat [Zheng+, 2023] (commit #e86e70d0)
- Question: [Nejumi LLM-Leaderboard NEO, mtbench_ja_question_v3](https://wandb.ai/wandb-japan/llm-leaderboard/artifacts/dataset/mtbench_ja_question/v3)
- Reference Answer: [Nejumi LLM-Leaderboard NEO, mtbench_ja_referenceanswer_v1](https://wandb.ai/wandb-japan/llm-leaderboard/artifacts/dataset/mtbench_ja_referenceanswer/v1)
- Prompt for Judge: [Nejumi LLM-Lederboard NEO, mtbench_ja_prompt_v1](https://wandb.ai/wandb-japan/llm-leaderboard/artifacts/dataset/mtbench_ja_prompt/v1)
- Judge: `gpt-4-1106-preview`
- Scoring: Absolute scale normalized to a 0-1 range, averaged over five runs.
## Usage
First install additional dependencies in [requirements.txt](./requirements.txt):
```sh
pip install -r requirements.txt
```
### Instruction format Ver0.1
This format must be adhered to strictly, as deviations may result in less optimal outputs from the model.
The template used to construct a prompt for the Instruct model is specified as follows:
```
<s>[INST] <<SYS>>\n{SYSTEM_PROMPT}\n<</SYS>>\n\n{USER_MESSAGE_1} [/INST] {BOT_MESSAGE_1}</s>[INST] {USER_MESSAGE_2} [/INST]
```
Please be aware that ``<s>`` and ``</s>`` are special tokens used for the beginning of string (BOS) and end of string (EOS), respectively, while [INST] and [/INST] are considered regular strings.
For the "{SYSTEM_PROMPT}" part, We recommend using "あなたは誠実で優秀な日本人のアシスタントです。"
For the "{USER_MESSAGE_1}" part, We recommend using {instruction}\n{input}
In other words, We recommend the following:
```
<s>[INST] <<SYS>>\nあなたは誠実で優秀な日本人のアシスタントです。\n<</SYS>>\n\n{instruction1}\n{input1} [/INST] {BOT_MESSAGE_1}</s>[INST] {instruction2}\n{input2} [/INST]
```
### Use the instruct model Ver0.1
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "tokyotech-llm/Swallow-70b-instruct-v0.1"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = "cuda"
messages = [
{"role": "system", "content": "あなたは誠実で優秀な日本人のアシスタントです。"},
{"role": "user", "content": "東京工業大学の主なキャンパスについて教えてください"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=128, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
```
## Training Datasets
### Instruction Tuning Ver0.1
The following datasets were used for the instruction tuning.
- [OpenAssistant Conversations Dataset EN top-1 thread](https://huggingface.co/datasets/OpenAssistant/oasst2)
- [OpenAssistant Conversations Dataset](https://huggingface.co/datasets/llm-jp/oasst1-21k-ja) was used, where human utterances are included but the responses are not used. Instead, the responses were generated using the [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) model.
## Risks and Limitations
The models released here are still in the early stages of our research and development and have not been tuned to ensure outputs align with human intent and safety considerations.
## Acknowledgements
We thank Meta Research for releasing Llama 2 under an open license for others to build on.
Our project is supported by the [ABCI Large-scale Language Model Building Support Program](https://abci.ai/en/link/llm_support_program.html) of the National Institute of Advanced Industrial Science and Technology.
## License
Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
## Authors
Here are the team members:
- From [Okazaki Laboratory](https://www.nlp.c.titech.ac.jp/index.en.html), the following members:
- [Naoaki Okazaki](https://www.chokkan.org/index.ja.html)
- [Sakae Mizuki](https://s-mizuki-nlp.github.io/)
- [Hiroki Iida](https://meshidenn.github.io/)
- [Mengsay Loem](https://loem-ms.github.io/)
- [Shota Hirai](https://huggingface.co/Kotemo428)
- [Kakeru Hattori](https://aya-se.vercel.app/)
- [Masanari Ohi](https://twitter.com/stjohn2007)
- From [YOKOTA Laboratory](https://www.rio.gsic.titech.ac.jp/en/index.html), the following members:
- [Rio Yokota](https://twitter.com/rioyokota)
- [Kazuki Fujii](https://twitter.com/okoge_kaz)
- [Taishi Nakamura](https://twitter.com/Setuna7777_2)
- [Takumi Okamoto](https://www.linkedin.com/in/takumi-okamoto)
- [Ishida Shigeki](https://www.wantedly.com/id/reborn27)
## How to cite
If you find our work helpful, please feel free to cite us.
```
@inproceedings{Fujii:COLM2024,
title={Continual Pre-Training for Cross-Lingual LLM Adaptation:
Enhancing Japanese Language Capabilities},
author={Kazuki Fujii and Taishi Nakamura and Mengsay Loem and Hiroki
Iida and Masanari Ohi and Kakeru Hattori and Hirai Shota and Sakae
Mizuki and Rio Yokota and Naoaki Okazaki},
booktitle="Proceedings of the First Conference on Language Modeling",
series={COLM},
pages="(to appear)",
year="2024",
month=oct,
address={University of Pennsylvania, USA},
}
@inproceedings{Okazaki:COLM2024,
title={Building a Large Japanese Web Corpus for Large Language Models},
author={Naoaki Okazaki and Kakeru Hattori and Hirai Shota and Hiroki
Iida and Masanari Ohi and Kazuki Fujii and Taishi Nakamura and Mengsay
Loem and Rio Yokota and Sakae Mizuki},
booktitle="Proceedings of the First Conference on Language Modeling",
series={COLM},
pages="(to appear)",
year="2024",
month=oct,
address={University of Pennsylvania, USA},
}
```

30
config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"_name_or_path": "tokyotech-llm/Swallow-7b-instruct-v0.1",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"max_sequence_length": 4096,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.39.0.dev0",
"use_cache": true,
"vocab_size": 43176
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

11
generation_config.json Normal file
View File

@@ -0,0 +1,11 @@
{
"bos_token_id": 1,
"do_sample": true,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.6,
"max_length": 4096,
"top_p": 0.9,
"transformers_version": "4.33.2"
}

3
logo.png Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a6948289c43c398d1c7a190767e3c68e30215015f44bdaa497836192fc9bbfa
size 1913917

3
model-00001-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b31c685486a7ae8b0fefc1e2479751d3fff6ccf997a766aaad4b20bf5da9588d
size 4940361496

3
model-00002-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5613829c8e4d4a72ab05687ce3ddf585e9003264f2278805aa068f58f128f126
size 4947390888

3
model-00003-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3a9b202bb29020fb4820bf2653b2f5a15df170017085a85af4547a035793ae6c
size 3772220264

298
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 13659938816
},
"weight_map": {
"lm_head.weight": "model-00003-of-00003.safetensors",
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.norm.weight": "model-00003-of-00003.safetensors"
}
}

5
requirements.txt Normal file
View File

@@ -0,0 +1,5 @@
torch
transformers
sentencepiece
accelerate
protobuf

24
special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c877c5ca885bad5c19d1b1706a2703f8b30de90f03c1f834f8bdb9faf79821e8
size 914000

36
tokenizer_config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true and not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = 'あなたは誠実で優秀な日本人のアシスタントです。' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{{ bos_token }}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + content.strip() + ' [/INST] ' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + content.strip() + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ '' + content.strip() + '' + eos_token }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}