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

Llama 3 Refueled by refuelai

 »  All LLMs  »  refuelai  »  Llama 3 Refueled   URL Share it on

  3348   
  Autotrain compatible   Conversational   Data labeling   En   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/refuelai/Llama-3-Refueled 

Llama 3 Refueled Benchmarks

MMLU Pro: 23.28
GPQA: 6.6
MUSR: 14.64
BBH: 41.72
IFEval: 46.2 vs 88 (so35)-47.5%
ARC: 54.61 vs 96.7 (so35)-43.5%
HellaSwag: 79.04 vs 95.3 (gpt4)-17.1%
MMLU: 64.73 vs 88.3 (so35)-26.7%
TruthfulQA: 41.77 vs 59 (gpt4)-29.2%
WinoGrande: 80.11 vs 87.5 (gpt4)-8.4%
GSM8K: 61.49 vs 96.4 (so35)-36.2%
MATH Lvl 5: 6.65
LLME Score: 0.29829
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 Refueled (refuelai/Llama-3-Refueled)

Llama 3 Refueled Parameters and Internals

Model Type 
auto-regressive, instruction tuned
Use Cases 
Areas:
data labeling
Limitations:
The Llama-3-Refueled does not have any moderation mechanisms.
Supported Languages 
en (high)
Training Details 
Data Sources:
Human annotated datasets like Flan, Task Source, and the Aya collection, Synthetic datasets like OpenOrca, OpenHermes and WizardLM, Proprietary datasets developed or licensed by Refuel AI
Data Volume:
over 4 Billion tokens
Model Architecture:
optimized transformer architecture
Input Output 
Input Format:
Text only.
Accepted Modalities:
text
Output Format:
Text only.
LLM NameLlama 3 Refueled
Repository 🤗https://huggingface.co/refuelai/Llama-3-Refueled 
Model Size8b
Required VRAM16.1 GB
Updated2025-05-31
Maintainerrefuelai
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   0.0 GB   0.0 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length8192
Model Max Length8192
Transformers Version4.39.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the Llama 3 Refueled

Model
Likes
Downloads
VRAM
Llama 3 Refueled AWQ1215 GB

Best Alternatives to Llama 3 Refueled

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3498107
UltraLong Thinking4192K / 16.1 GB3002
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB39015
Zero Llama 3.1 8B Beta61048K / 16.1 GB7301
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB180343
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB573
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB942
Note: green Score (e.g. "73.2") means that the model is better than refuelai/Llama-3-Refueled.

Rank the Llama 3 Refueled 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? 47753 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