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

Gemma 2B Orpo by anakin87

 »  All LLMs  »  anakin87  »  Gemma 2B Orpo   URL Share it on

  148   
  Arxiv:2403.07691   Autotrain compatible Base model:finetune:google/gem...   Base model:google/gemma-2b   Conversational Dataset:alvarobartt/dpo-mix-7k...   En   Endpoints compatible   Gemma   Generated from trainer   Model-index   Orpo   Region:us   Safetensors   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/anakin87/gemma-2b-orpo 

Gemma 2B Orpo Benchmarks

MMLU Pro: 3.4
GPQA: 1.57
MUSR: 4.13
BBH: 7.95
IFEval: 24.78 vs 88 (so35)-71.8%
ARC: 49.15 vs 96.7 (so35)-49.2%
HellaSwag: 73.72 vs 95.3 (gpt4)-22.6%
MMLU: 38.52 vs 88.3 (so35)-56.4%
TruthfulQA: 44.53 vs 59 (gpt4)-24.5%
WinoGrande: 64.33 vs 87.5 (gpt4)-26.5%
GSM8K: 13.87 vs 96.4 (so35)-85.6%
MATH Lvl 5: 1.28
LLME Score: 0.23523
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 2B Orpo (anakin87/gemma-2b-orpo)

Gemma 2B Orpo Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
text generation
Additional Notes 
The model is optimized to run smoothly on platforms such as Colab. It supports ORPO, which offers efficient training and memory usage benefits.
Supported Languages 
en (English)
Training Details 
Data Sources:
alvarobartt/dpo-mix-7k-simplified
Methodology:
The model uses ORPO (Odds Ratio Preference Optimization), integrating supervised fine-tuning and preference alignment phases.
LLM NameGemma 2B Orpo
Repository 🤗https://huggingface.co/anakin87/gemma-2b-orpo 
Base Model(s)  Gemma 2B   google/gemma-2b
Model Size2b
Required VRAM5.1 GB
Updated2025-02-05
Maintaineranakin87
Model Typegemma
Model Files  5.0 GB: 1-of-2   0.1 GB: 2-of-2   0.0 GB
Supported Languagesen
Model ArchitectureGemmaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.39.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Gemma 2B Orpo

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 1.1 2B It8K / 5.1 GB93340154
Codegemma 2B8K / 5.1 GB853778
Gemma Ko 1.1 2B It8K / 5.1 GB23911
EMO 2B8K / 5.1 GB43042
Octopus V28K / 5.1 GB935872
Gemma2b Lungcancerqa8K / 3.1 GB842
LION Gemma 2B Sft V1.08K / 5.1 GB1040
2B Or Not 2B8K / 5.1 GB5426
Gemma 2B Ko V08K / 5 GB2230
LION Gemma 2B Odpo V1.08K / 10 GB34
Note: green Score (e.g. "73.2") means that the model is better than anakin87/gemma-2b-orpo.

Rank the Gemma 2B Orpo 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? 42577 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 v20241227
  Support LLM Explorer