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

Delta 4B Super by frankenmerger

 »  All LLMs  »  frankenmerger  »  Delta 4B Super   URL Share it on

  5   
  Autotrain compatible   Conversational   Custom code   En   Endpoints compatible   Phi   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/frankenmerger/delta-4B-super 

Delta 4B Super Benchmarks

ARC: 58.62 vs 96.7 (so35)-39.4%
HellaSwag: 76.29 vs 95.3 (gpt4)-19.9%
MMLU: 59.06 vs 88.3 (so35)-33.1%
TruthfulQA: 51.74 vs 59 (gpt4)-12.3%
WinoGrande: 73.64 vs 87.5 (gpt4)-15.8%
GSM8K: 46.93 vs 96.4 (so35)-51.3%
LLME Score: 0.15718
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Delta 4B Super (frankenmerger/delta-4B-super)
🌟 Advertise your project 🚀

Delta 4B Super Parameters and Internals

Model Type 
text-generation
Additional Notes 
It is a frankenmerge of Phi-2-super.
LLM NameDelta 4B Super
Repository 🤗https://huggingface.co/frankenmerger/delta-4B-super 
Model Size4b
Required VRAM9.3 GB
Updated2025-09-23
Maintainerfrankenmerger
Model Typephi
Model Files  1.9 GB: 1-of-5   2.0 GB: 2-of-5   2.0 GB: 3-of-5   2.0 GB: 4-of-5   1.4 GB: 5-of-5
Supported Languagesen
Model ArchitecturePhiForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.38.2
Tokenizer ClassCodeGenTokenizer
Padding Token<|endoftext|>
Vocabulary Size51200
Torch Data Typebfloat16

Best Alternatives to Delta 4B Super

Best Alternatives
Context / RAM
Downloads
Likes
...hi 2 Upscaled 4B Instruct V0.12K / 8.1 GB43
Phi 2 4B2K / 1.8 GB100
Delta 4B Orange2K / 9.3 GB70
Delta 4B Notso Base2K / 9.3 GB620
Delta 4B Instruct V0.12K / 9.4 GB60
Note: green Score (e.g. "73.2") means that the model is better than frankenmerger/delta-4B-super.

Rank the Delta 4B Super 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? 51566 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