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

Bilingual GPT Neox 4B 8K by rinna

 »  All LLMs  »  rinna  »  Bilingual GPT Neox 4B 8K   URL Share it on

  1146   
  Arxiv:2306.15595   Arxiv:2404.01657   Autotrain compatible Base model:finetune:rinna/bili... Base model:rinna/bilingual-gpt...   Dataset:cc100   Dataset:eleutherai/pile   Dataset:mc4 Dataset:togethercomputer/redpa...   Dataset:wikipedia   En   Ext 8k   Gpt neox   Ja   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/rinna/bilingual-gpt-neox-4b-8k 

Bilingual GPT Neox 4B 8K Benchmarks

ARC: 28.58 vs 96.7 (so35)-70.4%
HellaSwag: 43.94 vs 95.3 (gpt4)-53.9%
MMLU: 25.38 vs 88.3 (so35)-71.3%
TruthfulQA: 47.48 vs 59 (gpt4)-19.5%
WinoGrande: 47.99 vs 87.5 (gpt4)-45.2%
LLME Score: 0.19125
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bilingual GPT Neox 4B 8K (rinna/bilingual-gpt-neox-4b-8k)

Bilingual GPT Neox 4B 8K Parameters and Internals

Model Type 
bilingual, language model, transformer-based
Use Cases 
Areas:
research, commercial applications
Additional Notes 
The model's standard configuration requires transformers version 4.31.0 or higher to operate correctly. Special attention to hyper-parameters is needed for optimal performance.
Supported Languages 
English (proficient), Japanese (proficient)
Training Details 
Data Sources:
Japanese CC-100, Japanese C4, The Pile, Redpajama, Wikipedia
Data Volume:
1.5 billion tokens
Methodology:
fine-tuning using RoPE positional interpolation
Context Length:
8192
Model Architecture:
A 36-layer, 2816-hidden-size transformer-based language model
Input Output 
Performance Tips:
Since the model is sensitive to decoding hyper-parameters (e.g., temperature, top_p, top_k, repetition_penalty), it is suggested to explore the best setting for your task.
LLM NameBilingual GPT Neox 4B 8K
Repository 🤗https://huggingface.co/rinna/bilingual-gpt-neox-4b-8k 
Base Model(s)  Bilingual GPT Neox 4B   rinna/bilingual-gpt-neox-4b
Model Size4b
Required VRAM7.7 GB
Updated2024-12-26
Maintainerrinna
Model Typegpt_neox
Model Files  7.7 GB   7.7 GB
Supported Languagesja en
Context Length8k
Model ArchitectureGPTNeoXForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Tokenizer ClassT5Tokenizer
Padding Token[PAD]
Vocabulary Size65536
Torch Data Typefloat16

Best Alternatives to Bilingual GPT Neox 4B 8K

Best Alternatives
Context / RAM
Downloads
Likes
Sft Tldr Pythia 1 4b2K / 5.7 GB7450
Bilingual GPT Neox 4B2K / 7.7 GB305629
...al GPT Neox 4B Instruction Ppo2K / 7.7 GB77115
Tora 4B2K / 7.6 GB162
...al GPT Neox 4B Instruction Sft2K / 7.6 GB53318
...x 4B Instruction Sft En Ja 84K2K / 7.6 GB191
StellarX 4B V0.22K / 16 GB11982
StellarX 4B V02K / 8.1 GB12381
StellarX 4B V0.2 GPTQ2K / 1.8 GB211
Note: green Score (e.g. "73.2") means that the model is better than rinna/bilingual-gpt-neox-4b-8k.

Rank the Bilingual GPT Neox 4B 8K 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