Bilingual GPT Neox 4B Instruction Sft En Ja 84K by ryota39

 ยป  All LLMs  ยป  ryota39  ยป  Bilingual GPT Neox 4B Instruction Sft En Ja 84K   URL Share it on

  Autotrain compatible Dataset:izumi-lab/llm-japanese...   Endpoints compatible   Gpt neox   Instruct   Region:us   Safetensors   Sharded   Tensorflow

Bilingual GPT Neox 4B Instruction Sft En Ja 84K Benchmarks

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 En Ja 84K (ryota39/bilingual-gpt-neox-4b-instruction-sft-en-ja-84k)

Bilingual GPT Neox 4B Instruction Sft En Ja 84K Parameters and Internals

Model Type 
text generation, translation
Additional Notes 
Instruction tuning focused on translation tasks, using customized data extraction from izumi-lab/llm-japanese-dataset.
Supported Languages 
Japanese (native), English (translation)
Training Details 
Data Sources:
izumi-lab/llm-japanese-dataset
Data Volume:
84,300 records
Methodology:
Fine-tuning for translation task
Training Time:
5 hours 39 minutes 37 seconds
Hardware Used:
1 x NVIDIA RTX A6000(VRAM48GB)
Input Output 
Input Format:
Sequential prompt structure with instructions
Accepted Modalities:
text
Output Format:
Japanese translation of input English text
LLM NameBilingual GPT Neox 4B Instruction Sft En Ja 84K
Repository ๐Ÿค—https://huggingface.co/ryota39/bilingual-gpt-neox-4b-instruction-sft-en-ja-84k 
Model Size4b
Required VRAM7.6 GB
Updated2024-12-26
Maintainerryota39
Model Typegpt_neox
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.6 GB: 2-of-2   0.0 GB   0.0 GB
Model ArchitectureGPTNeoXForCausalLM
Licensecc-by-sa-4.0
Context Length2048
Model Max Length2048
Transformers Version4.38.2
Vocabulary Size65536
Torch Data Typebfloat16

Best Alternatives to Bilingual GPT Neox 4B Instruction Sft En Ja 84K

Best Alternatives
Context / RAM
Downloads
Likes
...al GPT Neox 4B Instruction Ppo2K / 7.7 GB77115
Tora 4B2K / 7.6 GB162
...al GPT Neox 4B Instruction Sft2K / 7.6 GB53318
Note: green Score (e.g. "73.2") means that the model is better than ryota39/bilingual-gpt-neox-4b-instruction-sft-en-ja-84k.

Rank the Bilingual GPT Neox 4B Instruction Sft En Ja 84K Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217