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

DiscoPOP Zephyr 7B Gemma by SakanaAI

 »  All LLMs  »  SakanaAI  »  DiscoPOP Zephyr 7B Gemma   URL Share it on

  7085   
  Arxiv:2406.08414   Alignment-handbook   Autotrain compatible Base model:finetune:huggingfac... Base model:huggingfaceh4/zephy...   Conversational   Dataset:argilla/dpo-mix-7k   Endpoints compatible   Gemma   Generated from trainer   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/SakanaAI/DiscoPOP-zephyr-7b-gemma 

DiscoPOP Zephyr 7B Gemma Benchmarks

LLME Score: 0.26848
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DiscoPOP Zephyr 7B Gemma (SakanaAI/DiscoPOP-zephyr-7b-gemma)

DiscoPOP Zephyr 7B Gemma Parameters and Internals

Additional Notes 
This model is identical in training to HuggingFaceH4/zephyr-7b-gemma-v0.1, but uses DiscoPOP instead of DPO.
Training Details 
Data Sources:
argilla/dpo-mix-7k
Methodology:
DiscoPOP - Discovered Preference Optimization algorithm
LLM NameDiscoPOP Zephyr 7B Gemma
Repository 🤗https://huggingface.co/SakanaAI/DiscoPOP-zephyr-7b-gemma 
Base Model(s)  HuggingFaceH4/zephyr-7b-gemma-sft-v0.1   HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
Model Size7b
Required VRAM17.1 GB
Updated2024-12-21
MaintainerSakanaAI
Model Typegemma
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   2.1 GB: 4-of-4   0.0 GB
Model ArchitectureGemmaForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to DiscoPOP Zephyr 7B Gemma

Best Alternatives
Context / RAM
Downloads
Likes
Kaggle Math Model Gemma V112K / 17.1 GB240
Gemma 1.1 7B It8K / 17.1 GB15665267
SeaLLM 7B V2.58K / 17.1 GB1495849
SauerkrautLM Gemma 7B8K / 17.1 GB777813
Zephyr 7B Gemma V0.18K / 17.1 GB763121
... Codegemma 2 7B It Alpaca V1.38K / 17.1 GB190
Codegemma 7B8K / 17.1 GB3463170
Codegemma 7B It8K / 17.1 GB1964205
Gemma 7B Openhermes V0.808K / 17 GB74681
Gemma 1.1 7B It8K / 17.1 GB74343
Note: green Score (e.g. "73.2") means that the model is better than SakanaAI/DiscoPOP-zephyr-7b-gemma.

Rank the DiscoPOP Zephyr 7B Gemma 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? 40013 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