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

Nemotron 4 340B Instruct SafeTensors by failspy

 »  All LLMs  »  failspy  »  Nemotron 4 340B Instruct SafeTensors   URL Share it on

  140   
  Arxiv:2406.08673   Autotrain compatible   Endpoints compatible   Instruct   Nemotron   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/failspy/Nemotron-4-340B-Instruct-SafeTensors 

Nemotron 4 340B Instruct SafeTensors Benchmarks

LLME Score: 0.20195
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nemotron 4 340B Instruct SafeTensors (failspy/Nemotron-4-340B-Instruct-SafeTensors)

Nemotron 4 340B Instruct SafeTensors Parameters and Internals

Model Type 
text generation, chat
Use Cases 
Areas:
Synthetic Data Generation, Chat applications
Primary Use Cases:
Building personalized LLMs, Chat use-cases
Limitations:
Bias amplification, Toxic response potential
Considerations:
Developers should tailor use to relevant industry standards.
Additional Notes 
Currently no support for direct inference.
Supported Languages 
languages_supported (Multilingual (with focus on English)), proficiency_levels ()
Training Details 
Data Sources:
English based texts, 50+ natural languages, 40+ coding languages
Data Volume:
9 trillion tokens
Methodology:
Supervised Fine-tuning (SFT), Direct Preference Optimization (DPO), Reward-aware Preference Optimization (RPO)
Context Length:
4096
Training Time:
December 2023 to May 2024
Model Architecture:
Transformer Decoder (auto-regressive)
Safety Evaluation 
Methodologies:
Garak, AEGIS, Human Content Red Teaming
Risk Categories:
prompt injection, data leakage, critical risks
Responsible Ai Considerations 
Fairness:
NVIDIA has established policies for trustworthy AI.
Transparency:
Developers should ensure model usage meets industry standards.
Accountability:
Responsibility shared between developers and users.
Input Output 
Input Format:
System User {prompt} Assistant
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Keep system prompt empty for better performance.
LLM NameNemotron 4 340B Instruct SafeTensors
Repository 🤗https://huggingface.co/failspy/Nemotron-4-340B-Instruct-SafeTensors 
Model Size340b
Required VRAM326.8 GB
Updated2025-02-22
Maintainerfailspy
Model Typenemotron
Instruction-BasedYes
Model Files  16.3 GB: 1-of-97   6.9 GB: 2-of-97   6.9 GB: 3-of-97   6.9 GB: 4-of-97   6.9 GB: 5-of-97   6.9 GB: 6-of-97   6.9 GB: 7-of-97   6.9 GB: 8-of-97   6.9 GB: 9-of-97   6.9 GB: 10-of-97   6.9 GB: 11-of-97   6.9 GB: 12-of-97   6.9 GB: 13-of-97   6.9 GB: 14-of-97   6.9 GB: 15-of-97   6.9 GB: 16-of-97   6.9 GB: 17-of-97   6.9 GB: 18-of-97   6.9 GB: 19-of-97   6.9 GB: 20-of-97   6.9 GB: 21-of-97   6.9 GB: 22-of-97   6.9 GB: 23-of-97   6.9 GB: 24-of-97   6.9 GB: 25-of-97   6.9 GB: 26-of-97   6.9 GB: 27-of-97   6.9 GB: 28-of-97   6.9 GB: 29-of-97   6.9 GB: 30-of-97   6.9 GB: 31-of-97   6.9 GB: 32-of-97   6.9 GB: 33-of-97   6.9 GB: 34-of-97   6.9 GB: 35-of-97   6.9 GB: 36-of-97   6.9 GB: 37-of-97   6.9 GB: 38-of-97   6.9 GB: 39-of-97   6.9 GB: 40-of-97   6.9 GB: 41-of-97   6.9 GB: 42-of-97   6.9 GB: 43-of-97   6.9 GB: 44-of-97   6.9 GB: 45-of-97   6.9 GB: 46-of-97
Model ArchitectureNemotronForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.40.0.dev0
Vocabulary Size260000
Torch Data Typebfloat16

Best Alternatives to Nemotron 4 340B Instruct SafeTensors

Best Alternatives
Context / RAM
Downloads
Likes
Nemotron 4 340B Instruct Hf4K / 165.4 GB1204
Note: green Score (e.g. "73.2") means that the model is better than failspy/Nemotron-4-340B-Instruct-SafeTensors.

Rank the Nemotron 4 340B Instruct SafeTensors 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? 43470 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