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

CantoneseLLMChat V0.5 by hon9kon9ize

 »  All LLMs  »  hon9kon9ize  »  CantoneseLLMChat V0.5   URL Share it on

  174   
  Autotrain compatible   Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow   Yue
Model Card on HF 🤗: https://huggingface.co/hon9kon9ize/CantoneseLLMChat-v0.5 

CantoneseLLMChat V0.5 Benchmarks

MMLU Pro: 16.71
GPQA: 3.69
MUSR: 18.13
BBH: 20.76
IFEval: 32.31 vs 88 (so35)-63.3%
MATH Lvl 5: 3.1
LLME Score: 0.25643
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CantoneseLLMChat V0.5 (hon9kon9ize/CantoneseLLMChat-v0.5)

CantoneseLLMChat V0.5 Parameters and Internals

Model Type 
text generation
Use Cases 
Primary Use Cases:
Cantonese language understanding and generation tasks
Limitations:
Not suitable for other Chinese languages, May not be suitable for informal or dialectal Cantonese
Considerations:
The model may contain bias and misinformation, use with caution.
Additional Notes 
Model faces issues with mirror misalignment between written Chinese and Cantonese, and knowledge transfer across different languages.
Supported Languages 
yue (Fluent in Cantonese, including translated Hong Kong news, Wikipedia articles, subtitles, and open-sourced dialogue corpora.)
Training Details 
Data Sources:
Hong Kong news, Wikipedia articles, Subtitles, Open-sourced dialogue corpora
Data Volume:
400 million tokens
Input Output 
Input Format:
Chat template similar to ChatML
Accepted Modalities:
text
LLM NameCantoneseLLMChat V0.5
Repository 🤗https://huggingface.co/hon9kon9ize/CantoneseLLMChat-v0.5 
Model Size6.1b
Required VRAM24.2 GB
Updated2025-01-23
Maintainerhon9kon9ize
Model Typellama
Model Files  4.9 GB: 1-of-5   4.8 GB: 2-of-5   4.8 GB: 3-of-5   4.8 GB: 4-of-5   4.9 GB: 5-of-5
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.42.3
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64960
Torch Data Typefloat32

Best Alternatives to CantoneseLLMChat V0.5

Best Alternatives
Context / RAM
Downloads
Likes
...ntoneseLLMChat Preview202403264K / 12.1 GB6812
Open Lilm V24K / 24.2 GB62
Yi64K / 12.1 GB830
Carbide Tebet Loki4K / 12.1 GB180

Rank the CantoneseLLMChat V0.5 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? 41774 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