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

REBEL Llama 3 by Cornell-AGI

 »  All LLMs  »  Cornell-AGI  »  REBEL Llama 3   URL Share it on

  19   
  Arxiv:2404.16767   Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/meta-lla...   Conversational   Dataset:openbmb/ultrafeedback   En   Endpoints compatible   Instruct   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/Cornell-AGI/REBEL-Llama-3 

REBEL Llama 3 Benchmarks

LLME Score: 0.19637
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
REBEL Llama 3 (Cornell-AGI/REBEL-Llama-3)

REBEL Llama 3 Parameters and Internals

Model Type 
text generation
Additional Notes 
Inspired by REBEL framework; utilizes FsfairX-LLaMA3-RM-v0.1 as reward model
Supported Languages 
en (proficient)
Training Details 
Data Sources:
UltraFeedback
Methodology:
Reinforcement Learning via Regressing Relative Rewards (REBEL)
Model Architecture:
As implemented in Meta-Llama-3-8B-Instruct
LLM NameREBEL Llama 3
Repository 🤗https://huggingface.co/Cornell-AGI/REBEL-Llama-3 
Base Model(s)  Meta Llama 3 8B Instruct   meta-llama/Meta-Llama-3-8B-Instruct
Model Size8b
Required VRAM16.1 GB
Updated2025-01-15
MaintainerCornell-AGI
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token[PAD]
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to REBEL Llama 3

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB5282680
161024K / 16.1 GB1690
121024K / 16.1 GB600
MrRoboto ProLong 8B V4b1024K / 16.1 GB1070
MrRoboto ProLong 8B V1a1024K / 16.1 GB1080
MrRoboto ProLong 8B V2a1024K / 16.1 GB1020
MrRoboto ProLong 8B V4c1024K / 16.1 GB870
...o ProLongBASE Pt6 Unaligned 8B1024K / 16.1 GB710
8B Unaligned BASE V2b1024K / 16.1 GB980
MrRoboto ProLong 8B V2f1024K / 16.1 GB770
Note: green Score (e.g. "73.2") means that the model is better than Cornell-AGI/REBEL-Llama-3.

Rank the REBEL Llama 3 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? 41362 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