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

Llama 3.1 Minitron 4B Depth Base by nvidia

 »  All LLMs  »  nvidia  »  Llama 3.1 Minitron 4B Depth Base   URL Share it on

  3727   
  Arxiv:2009.03300   Arxiv:2407.14679   Arxiv:2408.11796   Autotrain compatible   En   Endpoints compatible   Llama   Llama-3   Nemo   Nvidia   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/Llama-3.1-Minitron-4B-Depth-Base 

Llama 3.1 Minitron 4B Depth Base Benchmarks

MMLU Pro: 19.98
GPQA: 1.79
MUSR: 10.7
BBH: 19.44
IFEval: 16.07 vs 88 (so35)-81.7%
MATH Lvl 5: 1.96
LLME Score: 0.26047
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Llama 3.1 Minitron 4B Depth Base Parameters and Internals

Model Type 
text-to-text
Use Cases 
Areas:
commercial, natural language generation tasks
Applications:
code generation, language understanding
Primary Use Cases:
5-shot performance, zero-shot performance, code generation
Limitations:
Model trained on potentially biased or toxic data, May amplify biases or return toxic responses
Considerations:
Developers should ensure model meets their industry's requirements
Supported Languages 
English (Proficient), Multilingual (Proficient)
Training Details 
Data Sources:
webpages, dialogue, articles, written materials
Data Volume:
94 billion tokens
Methodology:
Knowledge Distillation
Training Time:
July 29, 2024 - Aug 3, 2024
Model Architecture:
Transformer Decoder (Auto-Regressive Language Model)
Responsible Ai Considerations 
Fairness:
The model may contain societal biases.
Transparency:
Not explicitly stated
Accountability:
Recommended to be managed by user's internal model team
Mitigation Strategies:
Policies to develop Trustworthy AI, report vulnerabilities
Input Output 
Input Format:
String
Accepted Modalities:
Text
Output Format:
String
Performance Tips:
Works well within 8k characters or less
LLM NameLlama 3.1 Minitron 4B Depth Base
Repository 🤗https://huggingface.co/nvidia/Llama-3.1-Minitron-4B-Depth-Base 
Model Size4b
Required VRAM9.1 GB
Updated2025-06-09
Maintainernvidia
Model Typellama
Model Files  5.0 GB: 1-of-2   4.1 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.43.3
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16
Llama 3.1 Minitron 4B Depth Base (nvidia/Llama-3.1-Minitron-4B-Depth-Base)

Best Alternatives to Llama 3.1 Minitron 4B Depth Base

Best Alternatives
Context / RAM
Downloads
Likes
Xgen Small 4B Instruct R256K / 17.7 GB492
SJT 4B146K / 7.6 GB130
...lama 3.1 Nemotron Nano 4B V1.1128K / 9 GB1412488
...lama 3.1 Nemotron Nano 4B V1.1128K / 9 GB6264
Basqui R1 4B V1128K / 6.5 GB1941
Loxa 4B128K / 16 GB1540
CharGen V3 Mini128K / 9 GB506
Nemotron W 4b MagLight 0.1128K / 9.2 GB133
Nemotron W 4b Halo 0.1128K / 9.2 GB173
Aura 4B128K / 9 GB1011
Note: green Score (e.g. "73.2") means that the model is better than nvidia/Llama-3.1-Minitron-4B-Depth-Base.

Rank the Llama 3.1 Minitron 4B Depth 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? 48046 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