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

CantoneseLLMChat Preview20240326 by hon9kon9ize

 »  All LLMs  »  hon9kon9ize  »  CantoneseLLMChat Preview20240326   URL Share it on

  103   

CantoneseLLMChat Preview20240326 is an open-source language model by hon9kon9ize. Features: 6.1b LLM, VRAM: 12.1GB, Context: 4K, License: cc-by-nc-sa-4.0, LLM Explorer Score: 0.15, Arc: 52.6, HellaSwag: 69.1, MMLU: 59.2, GSM8K: 25.6.

  Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow   Yue
Model Card on HF 🤗: https://huggingface.co/hon9kon9ize/CantoneseLLMChat-preview20240326 

CantoneseLLMChat Preview20240326 Benchmarks

ARC: 52.56 vs 96.7 (so35)-45.6%
HellaSwag: 69.05 vs 95.3 (gpt4)-27.5%
MMLU: 59.19 vs 88.3 (so35)-33%
GSM8K: 25.63 vs 96.4 (so35)-73.4%
LLME Score: 0.15085
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CantoneseLLMChat Preview20240326 (hon9kon9ize/CantoneseLLMChat-preview20240326)
🌟 Advertise your project 🚀

CantoneseLLMChat Preview20240326 Parameters and Internals

Model Type 
Language Generation, Causal Language Model
Use Cases 
Areas:
Cantonese language understanding and generation
Limitations:
Might not be suitable for other Chinese languages, May contain bias and misinformation, Not suitable for informal or dialectal Cantonese
Additional Notes 
This is a preview version and will be deleted once the new version is released.
Supported Languages 
Cantonese (Fluent)
Training Details 
Data Sources:
Translated Hong Kong news, Wikipedia articles, Subtitles, Open-sourced dialogue corpora
Data Volume:
200 million tokens
Methodology:
Continual pretraining on Cantonese corpus
LLM NameCantoneseLLMChat Preview20240326
Repository 🤗https://huggingface.co/hon9kon9ize/CantoneseLLMChat-preview20240326 
Model Size6.1b
Required VRAM12.1 GB
Updated2026-05-08
Maintainerhon9kon9ize
Model Typellama
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   2.2 GB: 3-of-3
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-sa-4.0
Context Length4096
Model Max Length4096
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size65088
Torch Data Typebfloat16

Best Alternatives to CantoneseLLMChat Preview20240326

Best Alternatives
Context / RAM
Downloads
Likes
CantoneseLLMChat V0.54K / 24.2 GB379
Yi64K / 12.1 GB8510
Open Lilm V24K / 24.2 GB22
Carbide Tebet Loki4K / 12.1 GB50
Note: green Score (e.g. "73.2") means that the model is better than hon9kon9ize/CantoneseLLMChat-preview20240326.

Rank the CantoneseLLMChat Preview20240326 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? 53999 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer