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

PULI GPTrio by NYTK

 »  All LLMs  »  NYTK  »  PULI GPTrio   URL Share it on

  464   
  Autotrain compatible   En   Endpoints compatible   Gpt neox   Hu   Puli   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/NYTK/PULI-GPTrio 

PULI GPTrio Benchmarks

MMLU Pro: 1.52
GPQA: 2.13
MUSR: 5.33
BBH: 3.02
IFEval: 21.8 vs 88 (so35)-75.2%
ARC: 30.72 vs 96.7 (so35)-68.2%
HellaSwag: 53.49 vs 95.3 (gpt4)-43.9%
MMLU: 24.73 vs 88.3 (so35)-72%
TruthfulQA: 39.03 vs 59 (gpt4)-33.8%
WinoGrande: 57.77 vs 87.5 (gpt4)-34%
GSM8K: 0.76 vs 96.4 (so35)-99.2%
MATH Lvl 5: 1.21
LLME Score: 0.15221
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
PULI GPTrio (NYTK/PULI-GPTrio)
🌟 Advertise your project 🚀

PULI GPTrio Parameters and Internals

Model Type 
text-generation, trilingual
Use Cases 
Areas:
research, multilingual applications
Limitations:
max_seq_length = 2048, float16, vocab size: 150 016
Supported Languages 
hu (native), en (native), zh (native)
Training Details 
Data Sources:
Hungarian corpus, English corpus, Github, Chinese corpus
Data Volume:
Hungarian: 41.5B words (314 GB), English: 61.9B words (391 GB), Chinese: 98.7B Chinese characters (340 GB), 6 million Github documents (33 GB)
Methodology:
Trained with EleutherAI's GPT-NeoX
Context Length:
2048
Model Architecture:
GPT-NeoX
LLM NamePULI GPTrio
Repository 🤗https://huggingface.co/NYTK/PULI-GPTrio 
Model Size7.7b
Required VRAM15.4 GB
Updated2025-10-28
MaintainerNYTK
Model Typegpt_neox
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.2 GB: 3-of-4   1.2 GB: 4-of-4   9.9 GB: 1-of-2   5.6 GB: 2-of-2
Supported Languageshu en zh
Model ArchitectureGPTNeoXForCausalLM
Licensecc-by-nc-4.0
Context Length2048
Model Max Length2048
Transformers Version4.37.0
Tokenizer ClassGPTNeoXTokenizer
Beginning of Sentence Token<|endoftext|>
End of Sentence Token<|endoftext|>
Unk Token<|endoftext|>
Vocabulary Size150016
Torch Data Typefloat16
Errorsreplace

Rank the PULI GPTrio 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? 51545 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