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

Phi 2 DPO Renew1 by DUAL-GPO

 »  All LLMs  »  DUAL-GPO  »  Phi 2 DPO Renew1   URL Share it on

  6   
  Adapter   Alignment-handbook Base model:adapter:microsoft/p...   Base model:microsoft/phi-2   Custom code Dataset:huggingfaceh4/ultrafee...   Dpo   Finetuned   Generated from trainer   Lora   Peft   Phi   Region:us   Safetensors   Tensorboard   Trl
Model Card on HF 🤗: https://huggingface.co/DUAL-GPO/phi-2-dpo-renew1 

Phi 2 DPO Renew1 Benchmarks

ARC: 64.08 vs 96.7 (so35)-33.7%
HellaSwag: 77.45 vs 95.3 (gpt4)-18.7%
MMLU: 58.35 vs 88.3 (so35)-33.9%
TruthfulQA: 51.19 vs 59 (gpt4)-13.2%
WinoGrande: 73.32 vs 87.5 (gpt4)-16.2%
GSM8K: 52.24 vs 96.4 (so35)-45.8%
LLME Score: 0.16638
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 2 DPO Renew1 (DUAL-GPO/phi-2-dpo-renew1)
🌟 Advertise your project 🚀

Phi 2 DPO Renew1 Parameters and Internals

Training Details 
Data Sources:
HuggingFaceH4/ultrafeedback_binarized
LLM NamePhi 2 DPO Renew1
Repository 🤗https://huggingface.co/DUAL-GPO/phi-2-dpo-renew1 
Base Model(s)  Phi 2   microsoft/phi-2
Required VRAM0.2 GB
Updated2025-09-13
MaintainerDUAL-GPO
Model Files  0.2 GB   0.0 GB
Model ArchitectureAdapter
Licensemit
Model Max Length2048
Is Biasednone
Tokenizer ClassCodeGenTokenizer
Padding Token<|endoftext|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesdense|k_proj|v_proj|q_proj
LoRA Alpha128
LoRA Dropout0.05
R Param128

Best Alternatives to Phi 2 DPO Renew1

Best Alternatives
Context / RAM
Downloads
Likes
Nemo Kimi Lora0K / 1.8 GB300
Nemo Books Lora 40K / 1.8 GB70
Nemo Books Lora0K / 1.8 GB90
Phi 3 Mini 4K Instruct Sa V0.10K / 0 GB50
Francois KTO Lora0K / 0 GB110
Francois KTO Lora0K / 0 GB60
Rei V2 Kto0K / 0 GB130
...caaaf043da230d9a30d8e0ddcbe8790K / 0.4 GB110
...357cade9cc1096cecc35c34dba89920K / 1.3 GB100
Rei V2 Kto0K / 0 GB50
Note: green Score (e.g. "73.2") means that the model is better than DUAL-GPO/phi-2-dpo-renew1.

Rank the Phi 2 DPO Renew1 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? 51352 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