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 Instruction Ppo by rinna

 Β»  All LLMs  Β»  rinna  Β»  Bilingual GPT Neox 4B Instruction Ppo   URL Share it on

  1466   
  Arxiv:1707.06347   Arxiv:2203.02155   Arxiv:2404.01657   Autotrain compatible Base model:finetune:rinna/bili... Base model:rinna/bilingual-gpt...   Dataset:anthropic/hh-rlhf   En   Gpt neox   Instruct   Ja   Pytorch   Region:us   Safetensors
Model Card on HF πŸ€—: https://huggingface.co/rinna/bilingual-gpt-neox-4b-instruction-ppo 

Bilingual GPT Neox 4B Instruction Ppo Benchmarks

ARC: 28.24 vs 96.7 (so35)-70.8%
HellaSwag: 47.9 vs 95.3 (gpt4)-49.7%
MMLU: 23.12 vs 88.3 (so35)-73.8%
TruthfulQA: 43.5 vs 59 (gpt4)-26.3%
WinoGrande: 52.25 vs 87.5 (gpt4)-40.3%
LLME Score: 0.1583
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 Instruction Ppo (rinna/bilingual-gpt-neox-4b-instruction-ppo)
🌟 Advertise your project πŸš€

Bilingual GPT Neox 4B Instruction Ppo Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Applications:
instruction-following conversational agent
Primary Use Cases:
Bilingual text generation
Limitations:
Sensitive to decoding hyper-parameters.
Considerations:
Decoding hyper-parameters should be carefully chosen.
Additional Notes 
The model uses a sentencepiece-based tokenizer with a vocabulary size of 65,536.
Supported Languages 
ja (full proficiency), en (full proficiency)
Training Details 
Data Sources:
Anthropic/hh-rlhf
Methodology:
Supervised Fine-Tuning (SFT) and PPO-based Reinforcement Learning (RL)
Model Architecture:
36-layer, 2816-hidden-size transformer-based language model
Input Output 
Input Format:
A special format for conversation between 'ユーアー' and 'システム', ending with 'システム: '.
Accepted Modalities:
text
Output Format:
Textual response in the set language (Japanese/English)
Performance Tips:
Adjust decoding hyper-parameters for optimal performance.
LLM NameBilingual GPT Neox 4B Instruction Ppo
Repository πŸ€—https://huggingface.co/rinna/bilingual-gpt-neox-4b-instruction-ppo 
Base Model(s)  Bilingual GPT Neox 4B   rinna/bilingual-gpt-neox-4b
Model Size4b
Required VRAM7.7 GB
Updated2025-09-23
Maintainerrinna
Model Typegpt_neox
Instruction-BasedYes
Model Files  7.7 GB   7.8 GB
Supported Languagesja en
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 Instruction Ppo

Best Alternatives
Context / RAM
Downloads
Likes
...al GPT Neox 4B Instruction Sft2K / 7.6 GB143617
Tora 4B2K / 7.6 GB52
...x 4B Instruction Sft En Ja 84K2K / 7.6 GB61

Rank the Bilingual GPT Neox 4B Instruction Ppo Capabilities

πŸ†˜ 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? 51555 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