# Japanese optimization
Llm Jp 3.1 1.8b
Apache-2.0
LLM-jp-3.1-1.8b is a large language model developed by the National Institute of Informatics in Japan. Based on the LLM-jp-3 series, it incorporates instruction pre-training to enhance the instruction-following ability.
Large Language Model
Transformers Supports Multiple Languages

L
llm-jp
572
1
Stockmark 2 100B Instruct Beta
MIT
Stockmark-2-100B is a 100-billion parameter large language model focused on Japanese capabilities, pre-trained on 1.5 trillion tokens of multilingual data and enhanced with Japanese synthetic data for improved instruction following.
Large Language Model
Transformers Supports Multiple Languages

S
stockmark
1,004
9
EZO Llama 3.2 3B Instruct Dpoe
A Japanese-optimized model fine-tuned based on Meta AI's Llama 3.2, supporting multilingual text generation
Large Language Model
Transformers Supports Multiple Languages

E
AXCXEPT
1,561
7
Llama 3 Swallow 8B Instruct V0.1
A Japanese-optimized large language model built on Meta Llama 3, enhancing Japanese capabilities through continuous pre-training and improving instruction-following abilities through supervised fine-tuning.
Large Language Model
Transformers Supports Multiple Languages

L
tokyotech-llm
13.88k
20
Shisa V1 Llama3 8b
A Japanese-optimized large language model fine-tuned based on Meta-Llama-3-8B-Instruct, excelling in multiple Japanese benchmark tests
Large Language Model
Transformers

S
shisa-ai
28
6
Llama 3 Swallow 8B V0.1
A large Japanese - enhanced language model built on Meta Llama 3, which improves Japanese processing capabilities through continuous pre - training and instruction fine - tuning.
Large Language Model
Transformers Supports Multiple Languages

L
tokyotech-llm
2,230
10
Fugaku LLM 13B Instruct
Other
Fugaku-LLM is a domestically developed model pre-trained from scratch entirely on the supercomputer 'Fugaku', primarily using Japanese training data, excelling in Japanese language processing
Large Language Model
Transformers Supports Multiple Languages

F
Fugaku-LLM
320
28
Fugaku LLM 13B
Other
Fugaku-LLM is a domestically produced large language model in Japan, pre-trained from scratch using the supercomputer 'Fugaku.' It boasts high transparency and security, with particularly outstanding performance in Japanese.
Large Language Model
Transformers Supports Multiple Languages

F
Fugaku-LLM
25
123
Swallow MS 7b Instruct V0.1
Apache-2.0
Japanese-enhanced large language model continuously pre-trained based on Mistral-7B-v0.1
Large Language Model
Transformers Supports Multiple Languages

S
tokyotech-llm
48
14
Whisper Large V3 Japanese 4k Steps Ct2
MIT
This is a CTranslate2 converted version of the OpenAI Whisper large-v3 model, specifically fine-tuned for Japanese with an additional 4,000 training steps, supporting multilingual speech recognition.
Speech Recognition Supports Multiple Languages
W
JhonVanced
54
4
Japanese E5 Mistral 7b Slerp
MIT
A Japanese text embedding model created by merging E5 Mistral 7B Instruct and Japanese StableLM Base Gamma 7B, focusing on sentence similarity tasks
Text Embedding
Transformers Japanese

J
oshizo
94
7
ELYZA Japanese Llama 2 13b Fast Instruct
A Japanese-optimized model based on Llama 2, designed specifically to enhance the Japanese interaction experience.
Large Language Model
Transformers Supports Multiple Languages

E
elyza
1,109
23
ELYZA Japanese Llama 2 13b Instruct
ELYZA-japanese-Llama-2-13b is a model based on Llama 2 with additional pre-training to enhance Japanese language capabilities.
Large Language Model
Transformers Supports Multiple Languages

E
elyza
1,022
40
Calm2 7b
Apache-2.0
CyberAgentLM2 is a decoder-only language model pre-trained on 1.3 trillion tokens of publicly available Japanese and English datasets.
Large Language Model
Transformers Supports Multiple Languages

C
cyberagent
748
28
Youri 7b
A large language model that conducts continuous pre-training on a Japanese-English mixed dataset based on llama2-7b, with significantly improved performance on Japanese tasks.
Large Language Model
Transformers Supports Multiple Languages

Y
rinna
3,824
21
ELYZA Japanese Llama 2 7b Fast Instruct
A language model based on Llama2 architecture with extended Japanese capabilities through additional pre-training
Large Language Model
Transformers Supports Multiple Languages

E
elyza
1,576
75
ELYZA Japanese Llama 2 7b Instruct
A language model based on the Llama2 architecture with extended Japanese capabilities through additional pre-training
Large Language Model
Transformers Supports Multiple Languages

E
elyza
5,917
67
Featured Recommended AI Models