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

LingoWhale 8B by deeplang-ai

 »  All LLMs  »  deeplang-ai  »  LingoWhale 8B   URL Share it on

  249   
  Arxiv:2009.03300   Arxiv:2107.03374   Arxiv:2110.14168   Arxiv:2210.09261   Arxiv:2304.06364   Arxiv:2305.08322   Arxiv:2305.12474   Arxiv:2306.09212   Autotrain compatible   Custom code   En   Lingowhale   Pytorch   Region:us   Sharded   Zh
Model Card on HF 🤗: https://huggingface.co/deeplang-ai/LingoWhale-8B 

LingoWhale 8B Benchmarks

ARC: 80.1 vs 96.7 (so35)-17.2%
HellaSwag: 72.3 vs 95.3 (gpt4)-24.1%
MMLU: 60.1 vs 88.3 (so35)-31.9%
GSM8K: 51.6 vs 96.4 (so35)-46.5%
OpenCompas: 49.7 vs 73.3 (gpt4)-32.2%
Exam: 63 vs 77.2 (gpt4)-18.4%
Language: 39.9 vs 62 (gpt4)-35.6%
Knowledge: 40.7 vs 73.5 (gpt4)-44.6%
Understand: 62.8 vs 70 (gpt4)-10.3%
Reasoning: 46.5 vs 74.4 (gpt4)-37.5%
LLME Score: 0.12291
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LingoWhale 8B (deeplang-ai/LingoWhale-8B)
🌟 Advertise your project 🚀

LingoWhale 8B Parameters and Internals

Model Type 
text generation, bilingual language model
Use Cases 
Areas:
Research, Commercial applications
Applications:
Text generation, Bilingual tasks
Primary Use Cases:
Bilingual text processing, Content generation
Limitations:
Math calculations are relatively weak, May produce hallucinations
Considerations:
Understand issues and assess risks before use
Additional Notes 
Open for academic research and commercial use with permission.
Supported Languages 
en (Fluent), zh (Fluent)
Training Details 
Data Sources:
高质量中英数据
Data Volume:
数万亿token
Methodology:
预训练
Context Length:
8000
Input Output 
Input Format:
Primarily text input in Chinese and English
Accepted Modalities:
text
Output Format:
Generated text in Chinese and English
Performance Tips:
Utilize GPU for optimal performance
LLM NameLingoWhale 8B
Repository 🤗https://huggingface.co/deeplang-ai/LingoWhale-8B 
Model Size8b
Required VRAM16 GB
Updated2025-09-23
Maintainerdeeplang-ai
Model Typelingowhale
Model Files  2.5 GB: 1-of-7   2.4 GB: 2-of-7   2.4 GB: 3-of-7   2.4 GB: 4-of-7   2.4 GB: 5-of-7   2.4 GB: 6-of-7   1.5 GB: 7-of-7
Supported Languagesen zh
Model ArchitectureLingoWhaleForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.31.0
Tokenizer ClassLingoWhaleTokenizer
Beginning of Sentence Token<!!BOS!!>
End of Sentence Token<!!EOS!!>
Unk Token<!!UNK!!>
Vocabulary Size96000
Torch Data Typebfloat16

Rank the LingoWhale 8B 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? 51534 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