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

BRAG Llama 3.1 8B V0.1 by maximalists

 »  All LLMs  »  maximalists  »  BRAG Llama 3.1 8B V0.1   URL Share it on

  19   
  Autotrain compatible   Brag   Chatqa   Chatrag   Conversational   En   Endpoints compatible   Instruct   Llama   Llama3.1   Pytorch   Rag   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/maximalists/BRAG-Llama-3.1-8b-v0.1 

BRAG Llama 3.1 8B V0.1 Benchmarks

LLME Score: 0.18823
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
BRAG Llama 3.1 8B V0.1 (maximalists/BRAG-Llama-3.1-8b-v0.1)

BRAG Llama 3.1 8B V0.1 Parameters and Internals

Model Type 
Small Language Model (SLM), Retrieval-Augmented Generation (RAG)
Use Cases 
Areas:
RAG tasks with tables and text, Conversational chat
Limitations:
The model is specifically trained for short contexts and may not perform well with longer ones.
Considerations:
To avoid underperformance and potential for hallucinations, please use the recommended system prompt.
Additional Notes 
The model is part of the BRAG series and specifically adapted for RAG tasks.
Supported Languages 
en (Primary language of training and evaluation. Base model has multi-lingual capabilities.)
Input Output 
Input Format:
Message prompt format for using the model.
Accepted Modalities:
text
Performance Tips:
Use the system prompt to enhance performance and reduce hallucinations.
LLM NameBRAG Llama 3.1 8B V0.1
Repository 🤗https://huggingface.co/maximalists/BRAG-Llama-3.1-8b-v0.1 
Model Size8b
Required VRAM16.1 GB
Updated2025-06-01
Maintainermaximalists
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
Licensellama3.1
Context Length131072
Model Max Length131072
Transformers Version4.43.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to BRAG Llama 3.1 8B V0.1

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3482107
UltraLong Thinking4192K / 16.1 GB3122
...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 GB41815
Zero Llama 3.1 8B Beta61048K / 16.1 GB7301
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB179443
...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 GB932
Note: green Score (e.g. "73.2") means that the model is better than maximalists/BRAG-Llama-3.1-8b-v0.1.

Rank the BRAG Llama 3.1 8B V0.1 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? 47770 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