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

Nanbeige 16B Base Llama by duoqi

 »  All LLMs  »  duoqi  »  Nanbeige 16B Base Llama   URL Share it on

  1046   
  Autotrain compatible   En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/duoqi/Nanbeige-16B-Base-Llama 

Nanbeige 16B Base Llama Benchmarks

ARC: 56.48 vs 96.7 (so35)-41.6%
HellaSwag: 78.97 vs 95.3 (gpt4)-17.1%
MMLU: 63.34 vs 88.3 (so35)-28.3%
TruthfulQA: 42.6 vs 59 (gpt4)-27.8%
WinoGrande: 75.77 vs 87.5 (gpt4)-13.4%
GSM8K: 47.01 vs 96.4 (so35)-51.2%
LLME Score: 0.20733
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nanbeige 16B Base Llama (duoqi/Nanbeige-16B-Base-Llama)

Nanbeige 16B Base Llama Parameters and Internals

Model Type 
text generation
Supported Languages 
zh (Proficient), en (Proficient)
Training Details 
Data Sources:
high-quality internet corpus, various books, code
Data Volume:
2.5T Tokens
LLM NameNanbeige 16B Base Llama
Repository 🤗https://huggingface.co/duoqi/Nanbeige-16B-Base-Llama 
Model Size16b
Required VRAM31.6 GB
Updated2024-12-26
Maintainerduoqi
Model Typellama
Model Files  4.9 GB: 1-of-7   4.9 GB: 2-of-7   4.9 GB: 3-of-7   5.0 GB: 4-of-7   5.0 GB: 5-of-7   4.9 GB: 6-of-7   2.0 GB: 7-of-7
Supported Languageszh en
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.28.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size59136
Torch Data Typebfloat16

Best Alternatives to Nanbeige 16B Base Llama

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Investigator 16B128K / 7.6 GB280
...aid Blackroot Grand HORROR 16B8K / 33.8 GB310
...o Sft Ties Post Merge Auto DPO8K / 141.2 GB150
Nanbeige2 16B Chat4K / 31.6 GB9630
...ALAXY V03 Slimorca 1 Epoch 50k4K / 31.8 GB2000
...ca 1 Epoch 50k DPO 1 Epoch 30k4K / 31.8 GB870
GALAXY XB V.034K / 31.9 GB750
FusionNet SOLAR4K / 31.9 GB10661
Llama 2 16B Nastychat4K / 32.4 GB7608
Vinallama 16B Chat Franken4K / 31.6 GB191
Note: green Score (e.g. "73.2") means that the model is better than duoqi/Nanbeige-16B-Base-Llama.

Rank the Nanbeige 16B Base Llama 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? 40248 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 v20241217
  Support LLM Explorer