Total runs:
225
Run Growth:
171
Growth Rate:
96.07%
Sponsored by
APIMart
HachiML / Swallow-MS-7b-instruct-v0.1
Model's Last Updated: May 05 2024
text-generation
Introduction of Swallow-MS-7b-instruct-v0.1
Model Details of Swallow-MS-7b-instruct-v0.1
Swallow-MS-7b-v0.1
このモデルは tokyotech-llm/Swallow-MS-7b-instruct-v0.1 のtokenizer.chat_templateを以下に変更したものです。
tokenizer.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 %}
{% if not (messages[0]['role'] == 'assistant' and loop_messages|length > 0) %}
{{ bos_token }}
{% endif %}
{% for message in loop_messages %}
{% if (message['role'] == 'user') != ((loop.index0 + (1 if messages[0]['role'] == 'assistant' else 0)) % 2 == 0) %}
{{ raise_exception('Conversation roles must alternate starting from the first role.') }}
{% 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 %}"""
元のモデルのrevisionは
8b17f1c87697fb354952fa0d1018568e50bdff56
です。
Our Swallow-MS-7b-v0.1 model has undergone continual pre-training from the Mistral-7B-v0.1, primarily with the addition of Japanese language data.
Model Release Updates
We are excited to share the release schedule for our latest models:
- April 26, 2024 : Released the Swallow-MS-7b-instruct-v0.1
-
March 11, 2024
: Released the
Swallow-MS-7b-v0.1
This repository provides large language models developed by TokyoTech-LLM .
Model Details
- Model type : Please refer to Mistral 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
Turn-Wise Performance
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-MS-7b-instruct-v0.1 | 0.3411 | 0.3770 | 0.4290 | 0.3454 | 0.1040 | 0.2400 | 0.3677 | 0.3907 | 0.4750 |
First Turn
| Model | Average | Writing | Roleplay | Reasoning | Math | Coding | Extraction | STEM | Humanities |
|---|---|---|---|---|---|---|---|---|---|
| Swallow-MS-7b-instruct-v0.1 | 0.3699 | 0.4880 | 0.4260 | 0.3900 | 0.1080 | 0.2364 | 0.3780 | 0.4500 | 0.4800 |
Second Turn
| Model | Average | Writing | Roleplay | Reasoning | Math | Coding | Extraction | STEM | Humanities |
|---|---|---|---|---|---|---|---|---|---|
| Swallow-MS-7b-instruct-v0.1 | 0.3130 | 0.2624 | 0.4320 | 0.2996 | 0.1000 | 0.2430 | 0.3564 | 0.3291 | 0.4700 |
Comparison to the past model
We only provide the overall score in this section.
| Model | Average | Writing | Roleplay | Reasoning | Math | Coding | Extraction | STEM | Humanities |
|---|---|---|---|---|---|---|---|---|---|
| Swallow-MS-7b-instruct-v0.1 | 0.3411 | 0.3770 | 0.4290 | 0.3454 | 0.1040 | 0.2400 | 0.3677 | 0.3907 | 0.4750 |
| 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 |
Evaluation Benchmarks
MT-Bench JA
We used Japanese MT-Bench 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
- Reference Answer: Nejumi LLM-Leaderboard NEO, mtbench_ja_referenceanswer_v1
- Prompt for Judge: Nejumi LLM-Lederboard NEO, 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 :
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] \n\n{instruction2}\n{input2} [/INST]
Use the instruct model Ver0.1
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "tokyotech-llm/Swallow-MS-7b-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 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 model.
- OpenAssistant Conversations Dataset 21k Ja
- OpenAssistant Conversations Dataset 21k En
- Databricks Dolly 15k Ja
- Databricks Dolly 15k En
Please note that some of the data had issues with quality or format, so not all of it was used.
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 Mistral AI for releasing Mistral 7B v0.1 under an open license for others to build on.
Our project is supported by the ABCI Large-scale Language Model Building Support Program of the National Institute of Advanced Industrial Science and Technology.
License
apache-2.0
Authors
Here are the team members:
- From Okazaki Laboratory , the following members:
- From YOKOTA Laboratory , the following members:
Runs of HachiML Swallow-MS-7b-instruct-v0.1 on huggingface.co
28
Total runs
0
24-hour runs
-3
3-day runs
-3
7-day runs
16
30-day runs
More Information About Swallow-MS-7b-instruct-v0.1 huggingface.co Model
Url of Swallow-MS-7b-instruct-v0.1
Swallow-MS-7b-instruct-v0.1 huggingface.co Url
Provider of Swallow-MS-7b-instruct-v0.1 huggingface.co
Other API from HachiML
Updated:March 14 2024
Total runs:
130
Run Growth:
111
Growth Rate:
88.80%
Total runs:
89
Run Growth:
80
Growth Rate:
93.02%
Total runs:
36
Run Growth:
10
Growth Rate:
27.78%
Total runs:
31
Run Growth:
17
Growth Rate:
56.67%
Total runs:
28
Run Growth:
18
Growth Rate:
66.67%
Total runs:
27
Run Growth:
17
Growth Rate:
65.38%
Total runs:
26
Run Growth:
16
Growth Rate:
64.00%
Total runs:
24
Run Growth:
12
Growth Rate:
52.17%
Total runs:
24
Run Growth:
8
Growth Rate:
32.00%
Total runs:
22
Run Growth:
10
Growth Rate:
50.00%
Total runs:
22
Run Growth:
11
Growth Rate:
50.00%
Total runs:
21
Run Growth:
11
Growth Rate:
52.38%
Total runs:
21
Run Growth:
10
Growth Rate:
50.00%
Total runs:
21
Run Growth:
11
Growth Rate:
55.00%
Total runs:
21
Run Growth:
11
Growth Rate:
55.00%
Total runs:
20
Run Growth:
10
Growth Rate:
52.63%
Total runs:
20
Run Growth:
14
Growth Rate:
73.68%
Total runs:
19
Run Growth:
10
Growth Rate:
55.56%
Total runs:
19
Run Growth:
9
Growth Rate:
50.00%
Total runs:
19
Run Growth:
11
Growth Rate:
57.89%
Total runs:
19
Run Growth:
7
Growth Rate:
36.84%
Total runs:
19
Run Growth:
6
Growth Rate:
31.58%
Total runs:
19
Run Growth:
11
Growth Rate:
61.11%
Total runs:
19
Run Growth:
8
Growth Rate:
44.44%
Total runs:
18
Run Growth:
8
Growth Rate:
47.06%
Total runs:
18
Run Growth:
12
Growth Rate:
66.67%
Total runs:
18
Run Growth:
7
Growth Rate:
41.18%
Total runs:
18
Run Growth:
7
Growth Rate:
38.89%
Total runs:
18
Run Growth:
7
Growth Rate:
41.18%
Total runs:
18
Run Growth:
8
Growth Rate:
44.44%
Total runs:
18
Run Growth:
8
Growth Rate:
53.33%
Total runs:
18
Run Growth:
6
Growth Rate:
35.29%
Total runs:
18
Run Growth:
8
Growth Rate:
44.44%
Total runs:
17
Run Growth:
6
Growth Rate:
40.00%
Total runs:
17
Run Growth:
5
Growth Rate:
29.41%
Total runs:
17
Run Growth:
3
Growth Rate:
17.65%
Total runs:
17
Run Growth:
8
Growth Rate:
47.06%
Total runs:
16
Run Growth:
10
Growth Rate:
62.50%
Total runs:
16
Run Growth:
9
Growth Rate:
56.25%
Total runs:
16
Run Growth:
1
Growth Rate:
6.67%
Total runs:
16
Run Growth:
7
Growth Rate:
43.75%
Total runs:
16
Run Growth:
9
Growth Rate:
60.00%
Total runs:
16
Run Growth:
7
Growth Rate:
43.75%
Total runs:
16
Run Growth:
1
Growth Rate:
6.67%
Total runs:
16
Run Growth:
6
Growth Rate:
35.29%
Total runs:
16
Run Growth:
10
Growth Rate:
62.50%
Total runs:
16
Run Growth:
8
Growth Rate:
47.06%
Total runs:
15
Run Growth:
8
Growth Rate:
57.14%
Total runs:
15
Run Growth:
2
Growth Rate:
13.33%
Total runs:
15
Run Growth:
6
Growth Rate:
40.00%
Total runs:
15
Run Growth:
7
Growth Rate:
46.67%
Total runs:
15
Run Growth:
8
Growth Rate:
53.33%
Total runs:
15
Run Growth:
4
Growth Rate:
26.67%
Total runs:
15
Run Growth:
6
Growth Rate:
40.00%
Total runs:
15
Run Growth:
6
Growth Rate:
40.00%
Total runs:
15
Run Growth:
8
Growth Rate:
53.33%
Total runs:
15
Run Growth:
3
Growth Rate:
25.00%
Total runs:
14
Run Growth:
12
Growth Rate:
80.00%
Total runs:
14
Run Growth:
8
Growth Rate:
57.14%
Total runs:
14
Run Growth:
5
Growth Rate:
38.46%
Total runs:
14
Run Growth:
5
Growth Rate:
41.67%
Total runs:
14
Run Growth:
7
Growth Rate:
50.00%
Total runs:
14
Run Growth:
8
Growth Rate:
57.14%
Total runs:
14
Run Growth:
4
Growth Rate:
30.77%
Total runs:
14
Run Growth:
7
Growth Rate:
46.67%
Total runs:
14
Run Growth:
14
Growth Rate:
93.33%
Total runs:
14
Run Growth:
5
Growth Rate:
35.71%
Total runs:
14
Run Growth:
6
Growth Rate:
46.15%
Total runs:
13
Run Growth:
1
Growth Rate:
7.69%
Total runs:
13
Run Growth:
4
Growth Rate:
30.77%
Total runs:
13
Run Growth:
6
Growth Rate:
46.15%
Total runs:
13
Run Growth:
4
Growth Rate:
33.33%
Total runs:
13
Run Growth:
6
Growth Rate:
46.15%
Total runs:
13
Run Growth:
6
Growth Rate:
50.00%
Total runs:
13
Run Growth:
6
Growth Rate:
50.00%
Total runs:
13
Run Growth:
7
Growth Rate:
53.85%
Total runs:
13
Run Growth:
6
Growth Rate:
46.15%
Total runs:
13
Run Growth:
3
Growth Rate:
23.08%
Total runs:
13
Run Growth:
6
Growth Rate:
46.15%
Total runs:
13
Run Growth:
5
Growth Rate:
38.46%
Total runs:
13
Run Growth:
5
Growth Rate:
41.67%
Total runs:
13
Run Growth:
5
Growth Rate:
41.67%
Total runs:
13
Run Growth:
5
Growth Rate:
41.67%
Total runs:
13
Run Growth:
6
Growth Rate:
46.15%
Total runs:
13
Run Growth:
4
Growth Rate:
33.33%
Total runs:
13
Run Growth:
4
Growth Rate:
30.77%
Total runs:
12
Run Growth:
3
Growth Rate:
25.00%
Total runs:
12
Run Growth:
6
Growth Rate:
50.00%
Total runs:
12
Run Growth:
4
Growth Rate:
33.33%
Total runs:
12
Run Growth:
3
Growth Rate:
25.00%