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

Llama3 Chinese 8B Instruct by FlagAlpha

 »  All LLMs  »  FlagAlpha  »  Llama3 Chinese 8B Instruct   URL Share it on

  18709   
  Autotrain compatible   Chinese   Conversational   Custom code   Endpoints compatible   Instruct   Llama   Llama3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/FlagAlpha/Llama3-Chinese-8B-Instruct 

Llama3 Chinese 8B Instruct Benchmarks

ARC: 59.04 vs 96.7 (so35)-38.9%
HellaSwag: 78.23 vs 95.3 (gpt4)-17.9%
MMLU: 62.47 vs 88.3 (so35)-29.3%
TruthfulQA: 51.5 vs 59 (gpt4)-12.7%
WinoGrande: 73.95 vs 87.5 (gpt4)-15.5%
GSM8K: 55.8 vs 96.4 (so35)-42.1%
LLME Score: 0.22333
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3 Chinese 8B Instruct (FlagAlpha/Llama3-Chinese-8B-Instruct)
🌟 Advertise your project 🚀

Llama3 Chinese 8B Instruct Parameters and Internals

Model Type 
text generation, dialogue
Additional Notes 
Model variants and updates are hosted on the official GitHub and website
Supported Languages 
Chinese (high)
Input Output 
Input Format:
text prompt in chat format
Accepted Modalities:
text
Output Format:
generated text
Performance Tips:
Optimized for CUDA and torch float16 use
LLM NameLlama3 Chinese 8B Instruct
Repository 🤗https://huggingface.co/FlagAlpha/Llama3-Chinese-8B-Instruct 
Model Size8b
Required VRAM16.1 GB
Updated2025-08-31
MaintainerFlagAlpha
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.39.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Quantized Models of the Llama3 Chinese 8B Instruct

Model
Likes
Downloads
VRAM
Llama 3 Chinese 8B Instruct V311316 GB

Best Alternatives to Llama3 Chinese 8B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB11730118
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
UltraLong Thinking4192K / 16.1 GB112
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB109215
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB145350
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
Zero Llama 3.1 8B Beta61048K / 16.1 GB2291
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB183
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB143
Note: green Score (e.g. "73.2") means that the model is better than FlagAlpha/Llama3-Chinese-8B-Instruct.

Rank the Llama3 Chinese 8B Instruct 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? 51022 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