Total runs:
2.5M
Run Growth:
239.7K
Growth Rate:
9.74%
stabilityai / japanese-stablelm-base-beta-7b
Model's Last Updated: December 19 2023
text-generation
Introduction of japanese-stablelm-base-beta-7b
Model Details of japanese-stablelm-base-beta-7b
Japanese-StableLM-Base-Beta-7B
A cute robot wearing a kimono writes calligraphy with one single brush — Stable Diffusion XL
Model Description
japanese-stablelm-base-beta-7b
is a 7B-parameter decoder-only language model based on
Llama-2-7b
that has been fine-tuned on a diverse collection of Japanese data, with the intent of maximizing downstream performance on Japanese language tasks.
For an instruction-following model, check Japanese-StableLM-Instruct-Beta-7B . The base and instruct models are also available in larger 70b sizes. For a model that has faster inference times, see Japanese-StableLM-Base-JA_Vocab-Beta-7B , or the instruction-following version .
Usage
First install additional dependencies in requirements.txt :
pip install -r requirements.txt
Then start generating text with
japanese-stablelm-base-beta-7b
by using the following code snippet:
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "stabilityai/japanese-stablelm-base-beta-7b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
# The next line may need to be modified depending on the environment
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
prompt = """
AI で科学研究を加速するには、
""".strip()
input_ids = tokenizer.encode(
prompt,
add_special_tokens=True,
return_tensors="pt"
)
# this is for reproducibility.
# feel free to change to get different result
seed = 23
torch.manual_seed(seed)
tokens = model.generate(
input_ids.to(device=model.device),
max_new_tokens=128,
temperature=0.99,
top_p=0.95,
do_sample=True,
)
out = tokenizer.decode(tokens[0], skip_special_tokens=True)
print(out)
We suggest playing with different generation config (
top_p
,
repetition_penalty
etc) to find the best setup for your tasks. For example, use higher temperature for roleplay task, lower temperature for reasoning.
Model Details
-
Model type
:
japanese-stablelm-base-beta-7bmodel is an auto-regressive language model based on the Llama2 transformer architecture. - Language(s) : Japanese
- License : Llama2 Community License .
- Contact : For questions and comments about the model, please join Stable Community Japan . For future announcements / information about Stability AI models, research, and events, please follow https://twitter.com/StabilityAI_JP .
Training Dataset
Roughly 100B tokens from a mixture of the following corpora were used for continued pre-training.
- Japanese/English Wikipedia
- Japanese mc4
- Japanese CC-100
- Japanese OSCAR
- SlimPajama (excluding the Books3 subset)
Use and Limitations
Intended Use
The model is intended to be used by all individuals as a foundation for application-specific fine-tuning without strict limitations on commercial use.
Limitations and bias
The pre-training dataset may have contained offensive or inappropriate content even after applying data cleansing filters which can be reflected in the model generated text. We recommend users exercise reasonable caution when using these models in production systems. Do not use the model for any applications that may cause harm or distress to individuals or groups.
Authors
This model was developed by the Research & Development team at Stability AI Japan, and the development was co-led by Takuya Akiba and Meng Lee . The members of the team are as follows:
Acknowledgements
We thank Meta Research for releasing Llama 2 under an open license for others to build on.
We are grateful for the contributions of the EleutherAI Polyglot-JA team in helping us to collect a large amount of pre-training data in Japanese. Polyglot-JA members includes Hyunwoong Ko (Project Lead), Fujiki Nakamura (originally started this project when he commited to the Polyglot team), Yunho Mo, Minji Jung, KeunSeok Im, and Su-Kyeong Jang.
We are also appreciative of AI Novelist/Sta (Bit192, Inc.) and the numerous contributors from Stable Community Japan for assisting us in gathering a large amount of high-quality Japanese textual data for model training.
How to cite
@misc{JapaneseStableLMBaseBeta7B,
url={[https://huggingface.co/stabilityai/japanese-stablelm-base-beta-7b](https://huggingface.co/stabilityai/japanese-stablelm-base-beta-7b)},
title={Japanese StableLM Base Beta 7B},
author={Lee, Meng and Nakamura, Fujiki and Shing, Makoto and McCann, Paul and Akiba, Takuya and Orii, Naoki}
}
Runs of stabilityai japanese-stablelm-base-beta-7b on huggingface.co
274
Total runs
-18
24-hour runs
-22
3-day runs
-229
7-day runs
-5.0K
30-day runs
More Information About japanese-stablelm-base-beta-7b huggingface.co Model
Url of japanese-stablelm-base-beta-7b
japanese-stablelm-base-beta-7b huggingface.co Url
Provider of japanese-stablelm-base-beta-7b huggingface.co
Other API from stabilityai
Updated: October 31 2023
Total runs:
1.1M
Run Growth:
57.7K
Growth Rate:
5.48%
Total runs:
929.7K
Run Growth:
230.7K
Growth Rate:
25.49%
Total runs:
761.8K
Run Growth:
397.3K
Growth Rate:
55.85%
Total runs:
399.7K
Run Growth:
-111.0K
Growth Rate:
-29.87%
Total runs:
351.9K
Run Growth:
192.2K
Growth Rate:
55.94%
Total runs:
262.3K
Run Growth:
-224.1K
Growth Rate:
-77.74%
Total runs:
250.1K
Run Growth:
61.3K
Growth Rate:
24.98%
Total runs:
234.6K
Run Growth:
-77.1K
Growth Rate:
-43.16%
Total runs:
125.9K
Run Growth:
52.6K
Growth Rate:
42.89%
Total runs:
121.2K
Run Growth:
3.4K
Growth Rate:
3.56%
Total runs:
118.5K
Run Growth:
-126.5K
Growth Rate:
-109.08%
Total runs:
100.8K
Run Growth:
-10.4K
Growth Rate:
-10.15%
Total runs:
60.3K
Run Growth:
37.7K
Growth Rate:
35.58%
Total runs:
42.7K
Run Growth:
-12.3K
Growth Rate:
-29.24%
Total runs:
35.6K
Run Growth:
3.1K
Growth Rate:
8.68%
Total runs:
30.4K
Run Growth:
10.0K
Growth Rate:
33.84%
Total runs:
27.8K
Run Growth:
-598
Growth Rate:
-2.16%
Total runs:
27.1K
Run Growth:
-38.2K
Growth Rate:
-141.22%
Total runs:
24.9K
Run Growth:
2.2K
Growth Rate:
8.65%
Total runs:
18.2K
Run Growth:
-2.9K
Growth Rate:
-15.81%
Total runs:
17.7K
Run Growth:
10.4K
Growth Rate:
59.20%
Total runs:
16.1K
Run Growth:
4.4K
Growth Rate:
29.09%
Total runs:
15.8K
Run Growth:
9.2K
Growth Rate:
58.71%
Total runs:
10.7K
Run Growth:
2.2K
Growth Rate:
20.42%
Total runs:
9.6K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
8.5K
Run Growth:
1.6K
Growth Rate:
19.01%
Total runs:
8.3K
Run Growth:
-1.4K
Growth Rate:
-16.72%
Total runs:
8.2K
Run Growth:
-1.1K
Growth Rate:
-14.44%
Total runs:
6.5K
Run Growth:
319
Growth Rate:
4.97%
Total runs:
5.8K
Run Growth:
562
Growth Rate:
9.89%
Total runs:
5.3K
Run Growth:
-2.5K
Growth Rate:
-47.02%
Total runs:
4.8K
Run Growth:
-1.3K
Growth Rate:
-27.98%
Total runs:
4.6K
Run Growth:
-1.5K
Growth Rate:
-32.27%
Total runs:
4.4K
Run Growth:
-310
Growth Rate:
-6.99%
Total runs:
3.6K
Run Growth:
1.0K
Growth Rate:
29.91%
Total runs:
2.3K
Run Growth:
-637
Growth Rate:
-28.17%
Total runs:
1.9K
Run Growth:
-6.4K
Growth Rate:
-332.92%
Total runs:
1.8K
Run Growth:
-127
Growth Rate:
-7.29%
Total runs:
1.8K
Run Growth:
163
Growth Rate:
9.68%
Total runs:
1.6K
Run Growth:
-10
Growth Rate:
-0.67%
Total runs:
1.5K
Run Growth:
-299
Growth Rate:
-20.82%
Total runs:
1.5K
Run Growth:
-23
Growth Rate:
-1.57%
Total runs:
1.5K
Run Growth:
-389
Growth Rate:
-25.80%
Total runs:
1.2K
Run Growth:
239
Growth Rate:
20.71%
Total runs:
1.1K
Run Growth:
533
Growth Rate:
48.63%
Total runs:
1.1K
Run Growth:
150
Growth Rate:
14.01%
Total runs:
1.1K
Run Growth:
-1
Growth Rate:
-0.10%
Total runs:
1.0K
Run Growth:
153
Growth Rate:
15.81%
Total runs:
1.0K
Run Growth:
-212
Growth Rate:
-21.95%
Total runs:
995
Run Growth:
-216
Growth Rate:
-23.38%
Total runs:
767
Run Growth:
48
Growth Rate:
6.37%
Total runs:
724
Run Growth:
0
Growth Rate:
0.00%
Total runs:
697
Run Growth:
326
Growth Rate:
47.18%
Total runs:
690
Run Growth:
92
Growth Rate:
100.00%
Total runs:
600
Run Growth:
0
Growth Rate:
0.00%
Total runs:
582
Run Growth:
359
Growth Rate:
61.68%
Total runs:
569
Run Growth:
0
Growth Rate:
0.00%
Total runs:
535
Run Growth:
16
Growth Rate:
3.00%
Total runs:
512
Run Growth:
406
Growth Rate:
79.30%
Total runs:
407
Run Growth:
271
Growth Rate:
100.00%
Total runs:
360
Run Growth:
168
Growth Rate:
48.55%
Total runs:
358
Run Growth:
73
Growth Rate:
20.39%
Total runs:
346
Run Growth:
342
Growth Rate:
93.44%
Total runs:
321
Run Growth:
410
Growth Rate:
92.76%
Total runs:
318
Run Growth:
-25
Growth Rate:
-7.91%
Total runs:
308
Run Growth:
274
Growth Rate:
100.00%
Total runs:
223
Run Growth:
-192
Growth Rate:
-89.72%
Total runs:
202
Run Growth:
-171
Growth Rate:
-93.96%
Total runs:
171
Run Growth:
-290
Growth Rate:
-170.59%
Total runs:
169
Run Growth:
48
Growth Rate:
100.00%
Total runs:
146
Run Growth:
-262
Growth Rate:
-184.51%
Total runs:
141
Run Growth:
35
Growth Rate:
24.82%
Total runs:
133
Run Growth:
-326
Growth Rate:
-245.11%
Total runs:
112
Run Growth:
79
Growth Rate:
70.54%
Total runs:
94
Run Growth:
23
Growth Rate:
24.47%
Total runs:
74
Run Growth:
25
Growth Rate:
100.00%
Total runs:
66
Run Growth:
-82
Growth Rate:
-124.24%
Total runs:
40
Run Growth:
-20
Growth Rate:
-46.51%
Total runs:
20
Run Growth:
-21
Growth Rate:
-105.00%
Total runs:
8
Run Growth:
0
Growth Rate:
0.00%
Total runs:
6
Run Growth:
-11
Growth Rate:
-157.14%
Total runs:
5
Run Growth:
4
Growth Rate:
80.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%