Rinna Japanese GPT Neox Small Bnb 4bit Smashed by PrunaAI

 ยป  All LLMs  ยป  PrunaAI  ยป  Rinna Japanese GPT Neox Small Bnb 4bit Smashed   URL Share it on

  4-bit   4bit   Autotrain compatible Base model:prunaai/rinna-japan... Base model:quantized:prunaai/r...   Bitsandbytes   Endpoints compatible   Gpt neox   Pruna-ai   Quantized   Region:us   Safetensors

Rinna Japanese GPT Neox Small Bnb 4bit Smashed Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Rinna Japanese GPT Neox Small Bnb 4bit Smashed (PrunaAI/rinna-japanese-gpt-neox-small-bnb-4bit-smashed)

Rinna Japanese GPT Neox Small Bnb 4bit Smashed Parameters and Internals

Model Type 
text generation
Additional Notes 
The model is compressed with techniques outlined by PrunaAI. The first run may take more memory or be slower.
Training Details 
Data Sources:
WikiText
Methodology:
Compression suggested by PrunaAI
Input Output 
Input Format:
Tokenized text input
Accepted Modalities:
text
Output Format:
Generated text
Performance Tips:
Run efficiency tests under your specific use-case conditions.
LLM NameRinna Japanese GPT Neox Small Bnb 4bit Smashed
Repository ๐Ÿค—https://huggingface.co/PrunaAI/rinna-japanese-gpt-neox-small-bnb-4bit-smashed 
Base Model(s)  ...PT Neox Small Bnb 4bit Smashed   PrunaAI/rinna-japanese-gpt-neox-small-bnb-4bit-smashed
Model Size95.6m
Required VRAM0.1 GB
Updated2025-01-20
MaintainerPrunaAI
Model Typegpt_neox
Model Files  0.1 GB
Quantization Type4bit
Model ArchitectureGPTNeoXForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.40.0
Tokenizer ClassT5Tokenizer
Padding Token[PAD]
Vocabulary Size44416
Torch Data Typefloat16

Quantized Models of the Rinna Japanese GPT Neox Small Bnb 4bit Smashed

Model
Likes
Downloads
VRAM
...PT Neox Small Bnb 4bit Smashed0180 GB

Best Alternatives to Rinna Japanese GPT Neox Small Bnb 4bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
Eleuther Pythia70m Hh DPO2K / 0.3 GB2750
Eleuther Pythia70m Hh Sft2K / 0.3 GB1380

Rank the Rinna Japanese GPT Neox Small Bnb 4bit Smashed 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? 41636 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227