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

Japanese Stablelm 3B 4e1t Base by stabilityai

 »  All LLMs  »  stabilityai  »  Japanese Stablelm 3B 4e1t Base   URL Share it on

  826   
  Arxiv:1607.06450   Arxiv:1910.07467   Arxiv:2104.09864   Arxiv:2204.06745   Arxiv:2307.09288   Autotrain compatible   Custom code   Dataset:cc100 Dataset:cerebras/slimpajama-62...   Dataset:mc4 Dataset:oscar-corpus/oscar-220... Dataset:oscar-corpus/oscar-230...   Dataset:wikipedia   Ja   Japanese-stablelm   Region:us   Safetensors   Stablelm epoch
Model Card on HF 🤗: https://huggingface.co/stabilityai/japanese-stablelm-3b-4e1t-base 

Japanese Stablelm 3B 4e1t Base Benchmarks

LLME Score: 0.12349
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Japanese Stablelm 3B 4e1t Base (stabilityai/japanese-stablelm-3b-4e1t-base)
🌟 Advertise your project 🚀

Japanese Stablelm 3B 4e1t Base Parameters and Internals

Model Type 
text generation, causal-lm
Use Cases 
Areas:
research, commercial applications
Limitations:
Contains offensive or inappropriate content even after data cleansing
Considerations:
Exercise caution in production systems
Additional Notes 
Not suitable for applications that may harm or distress individuals or groups.
Supported Languages 
ja (primary)
Training Details 
Data Sources:
https://dumps.wikimedia.org/other/cirrussearch, https://huggingface.co/datasets/mc4, http://data.statmt.org/cc-100/ja.txt.xz, https://oscar-project.github.io/documentation/, https://huggingface.co/datasets/cerebras/SlimPajama-627B
Data Volume:
~100B tokens
Methodology:
Continued pretraining of an English language model on Japanese data.
Context Length:
4096
Model Architecture:
decoder-only transformer with modifications
Input Output 
Accepted Modalities:
text
LLM NameJapanese Stablelm 3B 4e1t Base
Repository 🤗https://huggingface.co/stabilityai/japanese-stablelm-3b-4e1t-base 
Model Size3b
Required VRAM5.6 GB
Updated2025-09-23
Maintainerstabilityai
Model Typestablelm_epoch
Model Files  5.6 GB
Supported Languagesja
Model ArchitectureStableLMEpochForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.34.0.dev0
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50304
Torch Data Typebfloat16

Best Alternatives to Japanese Stablelm 3B 4e1t Base

Best Alternatives
Context / RAM
Downloads
Likes
Stable Code 3B Mlx16K / 5.6 GB241
Aura 3B4K / 5.6 GB12
Slim Extract4K / 5.6 GB1212
Slim Boolean4K / 5.6 GB104
Slim Sa Ner4K / 5.6 GB76
Slim Tags 3B4K / 5.6 GB84
Slim Summary4K / 5.6 GB108
Slim Xsum4K / 5.6 GB36
Memphis CoT 3B4K / 5.6 GB1030
Tofu 3B4K / 5.6 GB42
Note: green Score (e.g. "73.2") means that the model is better than stabilityai/japanese-stablelm-3b-4e1t-base.

Rank the Japanese Stablelm 3B 4e1t Base 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? 51545 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 v20241124
  Support LLM Explorer