LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Japanese Large Lm 3.6B by line-corporation

 »  All LLMs  »  line-corporation  »  Japanese Large Lm 3.6B   URL Share it on

  713   
  Autotrain compatible   Dataset:cc100   Dataset:mc4   Dataset:oscar   Dataset:wikipedia   Endpoints compatible   Gpt neox   Ja   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/line-corporation/japanese-large-lm-3.6b 

Japanese Large Lm 3.6B Benchmarks

LLME Score: 0.13222
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Japanese Large Lm 3.6B (line-corporation/japanese-large-lm-3.6b)

Japanese Large Lm 3.6B Parameters and Internals

Model Type 
text generation, Japanese language model
Use Cases 
Areas:
Research, Commercial applications
Applications:
Text generation, Japanese language applications
Primary Use Cases:
Japanese text generation, Japanese language applications
Additional Notes 
Uses a sentencepiece tokenizer with a unigram language model and byte-fallback. Does not apply pre-tokenization.
Supported Languages 
ja (high proficiency)
Training Details 
Data Sources:
wikipedia, mc4, cc100, oscar, Web texts crawled by in-house system
Data Volume:
650 GB
Methodology:
Standard language model training
Model Architecture:
GPTNeoX with RoPE for position encoding
Input Output 
Input Format:
Raw Japanese sentences
Accepted Modalities:
text
Output Format:
Generated text in Japanese
Performance Tips:
Use GPU for faster inference and setting the seed for reproducibility
LLM NameJapanese Large Lm 3.6B
Repository 🤗https://huggingface.co/line-corporation/japanese-large-lm-3.6b 
Model Size3.6b
Required VRAM7.2 GB
Updated2025-02-22
Maintainerline-corporation
Model Typegpt_neox
Model Files  7.2 GB   7.2 GB
Supported Languagesja
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.29.2
Tokenizer ClassT5Tokenizer
Padding Token<pad>
Vocabulary Size51200
Torch Data Typefloat16

Best Alternatives to Japanese Large Lm 3.6B

Best Alternatives
Context / RAM
Downloads
Likes
Japanese GPT Neox 3.6B2K / 7.4 GB380598
...y Jimba Japanese Large Lm 3.6B2K / 7.1 GB640
...rrowSmartPlus 3.6B Instruction2K / 14.3 GB51
...rrowSmartPlus 3.6B Instant Sft2K / 14.3 GB71
...rtPlus 3.6B Instant Sft JHSVer2K / 14.3 GB91
...T Neox 3.6B Instruction Sft V22K / 7.4 GB5463826
... Large Lm 3.6B Instruction Sft2K / 7.2 GB89025
... GPT Neox 3.6B Instruction Ppo2K / 7.4 GB258770
... GPT Neox 3.6B Instruction Sft2K / 7.4 GB900101
...tion Sft 8bit 1g Actorder True2K / 2.8 GB843
Note: green Score (e.g. "73.2") means that the model is better than line-corporation/japanese-large-lm-3.6b.

Rank the Japanese Large Lm 3.6B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 43508 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer