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

ADELIE DPO by THU-KEG

 »  All LLMs  »  THU-KEG  »  ADELIE DPO   URL Share it on

  25   
  Arxiv:2405.05008   Autotrain compatible   Dataset:ace05   Dataset:conll2003   Dataset:conll2012 ontonotesv5   Dataset:fewrel   Dataset:maven   Dataset:rams   Dataset:tacred   En   Endpoints compatible   Event extraction   Ie   Information extraction   Llama   Named entity recogniton   Pytorch   Region:us   Relation extraction   Sharded
Model Card on HF 🤗: https://huggingface.co/THU-KEG/ADELIE-DPO 

ADELIE DPO Benchmarks

LLME Score: 0.1566
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ADELIE DPO (THU-KEG/ADELIE-DPO)
🌟 Advertise your project 🚀

ADELIE DPO Parameters and Internals

Model Type 
Text Generation
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
closed IE, open IE, on-demand IE
Additional Notes 
Developed to align large language models on information extraction tasks effectively.
Supported Languages 
English (NLP)
Training Details 
Data Sources:
IEInstruct, alignment corpus
Methodology:
Instruction tuning with Direct Preference Optimization (DPO)
LLM NameADELIE DPO
Repository 🤗https://huggingface.co/THU-KEG/ADELIE-DPO 
Required VRAM13.5 GB
Updated2025-09-07
MaintainerTHU-KEG
Model Typellama
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   3.6 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length2048
Model Max Length2048
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<pad>
Vocabulary Size32001
Torch Data Typebfloat16

Best Alternatives to ADELIE DPO

Best Alternatives
Context / RAM
Downloads
Likes
LWM Text 512K512K / 13.5 GB82
LWM Text Chat 512K512K / 13.5 GB52
LWM Text Chat 256K256K / 13.5 GB93
LWM Text 256K256K / 13.5 GB83
Pallas 0.5 LASER 0.1195K / 68.9 GB18642
Orpheus AUS128K /  GB100
Finetuning Health Ci128K / 6.5 GB92
Ukr Synth Phi 3.5128K / 7.6 GB90
WizardLM Phi 3.5128K / 7.6 GB80
Ashley3b X 1.2128K / 6.5 GB250
Note: green Score (e.g. "73.2") means that the model is better than THU-KEG/ADELIE-DPO.

Rank the ADELIE DPO 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? 51187 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