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

Minitron 8B Base by nvidia

 »  All LLMs  »  nvidia  »  Minitron 8B Base   URL Share it on

  19126   
  Arxiv:2009.03300   Arxiv:2407.14679   Autotrain compatible   En   Endpoints compatible   Llama-3   Nemo   Nemotron   Nvidia   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/nvidia/Minitron-8B-Base 

Minitron 8B Base Benchmarks

MMLU Pro: 24.23
GPQA: 3.13
MUSR: 9.09
BBH: 22.04
IFEval: 24.24 vs 88 (so35)-72.5%
MATH Lvl 5: 2.57
LLME Score: 0.26697
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Minitron 8B Base (nvidia/Minitron-8B-Base)
🌟 Advertise your project 🚀

Minitron 8B Base Parameters and Internals

Model Type 
text generation, auto-regressive
Use Cases 
Areas:
research, development
Applications:
Multitask language understanding, code generation
Limitations:
Contains biases from internet-crawled data, May emit toxic or biased content
Considerations:
Developers must ensure use case requirements and address model misuse
Additional Notes 
Performance improvements achieved with fewer training tokens per model.
Supported Languages 
languages (/text), proficiency_levels (English and multilingual, including code)
Training Details 
Data Sources:
continuous pre-training data corpus from Nemotron-4 15B
Data Volume:
94 billion tokens
Methodology:
Pruning, knowledge distillation, continued training
Training Time:
Feb 2024 - June 2024
Hardware Used:
NVIDIA A100
Model Architecture:
Transformer Decoder
Responsible Ai Considerations 
Fairness:
Efforts required by developers to ensure meeting industry and use case requirements.
Accountability:
Shared responsibility promoted by NVIDIA
Mitigation Strategies:
Establish policies and practices to address product misuse.
Input Output 
Input Format:
String
Output Format:
String
Release Notes 
Version:
Minitron-8B-Base
Date:
February 2024 - June 2024
Notes:
Pruned and distilled from Nemotron-4 15B, achieving compute cost savings and improved performance.
LLM NameMinitron 8B Base
Repository 🤗https://huggingface.co/nvidia/Minitron-8B-Base 
Model Size8b
Required VRAM16.5 GB
Updated2025-09-23
Maintainernvidia
Model Typenemotron
Model Files  16.5 GB
Supported Languagesen
Model ArchitectureNemotronForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.44.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Minitron 8B Base

Best Alternatives
Context / RAM
Downloads
Likes
Nemotron3 8B4K / 17.1 GB8480

Rank the Minitron 8B Base 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? 51544 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