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

GPT R by digitous

 »  All LLMs  »  digitous  »  GPT R   URL Share it on

  1841   
  Autotrain compatible   En   Endpoints compatible   Gptj   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/digitous/GPT-R 

GPT R Benchmarks

ARC: 41.21 vs 96.7 (so35)-57.4%
HellaSwag: 66.89 vs 95.3 (gpt4)-29.8%
MMLU: 36.5 vs 88.3 (so35)-58.7%
TruthfulQA: 34.22 vs 59 (gpt4)-42%
WinoGrande: 64.4 vs 87.5 (gpt4)-26.4%
GSM8K: 1.59 vs 96.4 (so35)-98.4%
LLME Score: 0.12026
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GPT R (digitous/GPT-R)
🌟 Advertise your project 🚀

GPT R Parameters and Internals

Model Type 
Text Generation
Use Cases 
Primary Use Cases:
Natural language tasks such as writing and formatting articles, Base for merging with conversational or story writing models
Additional Notes 
Weight merge Script credit to Concedo
Supported Languages 
en (unknown)
Training Details 
Data Sources:
reciprocate/hh_eval_ilql, Anthropic/hh-rlhf, the_pile, bigscience/P3, allenai/natural-instructions
Methodology:
Weight merge of ppo_hh_gpt-j and GPT-JT-6B-v1 using a 60/40 blend (weighted average). Blend was done in FP32 and output in FP16.
Input Output 
Accepted Modalities:
Text
LLM NameGPT R
Repository 🤗https://huggingface.co/digitous/GPT-R 
Required VRAM12.3 GB
Updated2025-09-23
Maintainerdigitous
Model Typegptj
Model Files  2.1 GB: 1-of-6   2.1 GB: 2-of-6   2.1 GB: 3-of-6   2.1 GB: 4-of-6   2.0 GB: 5-of-6   1.9 GB: 6-of-6
Supported Languagesen
Model ArchitectureGPTJForCausalLM
Licensebigscience-openrail-m
Model Max Length1024
Transformers Version4.24.0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size50400
Torch Data Typefloat16
Activation Functiongelu_new

Best Alternatives to GPT R

Best Alternatives
Context / RAM
Downloads
Likes
DiffMerge DollyGPT Pygmalion0K / 12.1 GB18792
...Merge Pygmalion Main Onto V8P40K / 12.3 GB18921
Skegma GPTJ0K / 12.3 GB18280
Javalion GPTJ0K / 12.3 GB18301
Javalion R0K / 12.3 GB18265
Adventien GPTJ0K / 12.3 GB18140
Javelin R0K / 12.3 GB18202
Janin GPTJ0K / 12.3 GB18170
Javelin GPTJ0K / 12.3 GB18174
Janin R0K / 12.3 GB18231
Note: green Score (e.g. "73.2") means that the model is better than digitous/GPT-R.

Rank the GPT R 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? 51544 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