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 Sft by rinna

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

  533   
  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-sft 

Bilingual GPT Neox 4B Instruction Sft Benchmarks

ARC: 28.07 vs 96.7 (so35)-71%
HellaSwag: 47.5 vs 95.3 (gpt4)-50.2%
MMLU: 23.12 vs 88.3 (so35)-73.8%
TruthfulQA: 43.76 vs 59 (gpt4)-25.8%
WinoGrande: 52.33 vs 87.5 (gpt4)-40.2%
LLME Score: 0.18352
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 Sft (rinna/bilingual-gpt-neox-4b-instruction-sft)

Bilingual GPT Neox 4B Instruction Sft Parameters and Internals

Model Type 
bilingual, text generation, instruction-following, conversational agent
Use Cases 
Areas:
Research, Commercial applications
Applications:
Language translation, Conversational agents, Text generation
Primary Use Cases:
Instruction-following conversational agent
Additional Notes 
Ensure to use 'use_fast=False' for the tokenizer for correct functionality.
Supported Languages 
ja (high), en (high)
Training Details 
Data Sources:
Anthropic HH RLHF data, FLAN Instruction Tuning data, Japanese translations
Methodology:
Fine-tuning
Model Architecture:
36-layer, 2816-hidden-size transformer-based language model
Input Output 
Input Format:
A conversation format between 'ユーアー' and 'システム', ending with 'システム: '.
Accepted Modalities:
text
Output Format:
Text response from the system in continuation of the conversation.
Performance Tips:
Adjust decoding hyper-parameters (e.g., temperature, top_p, top_k) for optimal results.
Release Notes 
Version:
2023/08/02
Date:
2023-08-02
Notes:
Newly trained model with MIT license.
Version:
2023/07/31
Date:
2023-07-31
Notes:
Initial release found with non-compliant training data leading to a re-release with compliant datasets.
LLM NameBilingual GPT Neox 4B Instruction Sft
Repository πŸ€—https://huggingface.co/rinna/bilingual-gpt-neox-4b-instruction-sft 
Base Model(s)  Bilingual GPT Neox 4B   rinna/bilingual-gpt-neox-4b
Model Size4b
Required VRAM7.6 GB
Updated2024-12-26
Maintainerrinna
Model Typegpt_neox
Instruction-BasedYes
Model Files  7.6 GB   7.6 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 Sft

Best Alternatives
Context / RAM
Downloads
Likes
...al GPT Neox 4B Instruction Ppo2K / 7.7 GB77115
Tora 4B2K / 7.6 GB162
...x 4B Instruction Sft En Ja 84K2K / 7.6 GB191
Note: green Score (e.g. "73.2") means that the model is better than rinna/bilingual-gpt-neox-4b-instruction-sft.

Rank the Bilingual GPT Neox 4B Instruction Sft 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? 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