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

Dbrx Instruct 4.25bpw EXL2 by ek826

 »  All LLMs  »  ek826  »  Dbrx Instruct 4.25bpw EXL2   URL Share it on

  4   
  Arxiv:2211.15841   Arxiv:2304.11277   Autotrain compatible   Custom code   Dbrx   Exl2   Instruct   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ek826/dbrx-instruct-4.25bpw-exl2 

Dbrx Instruct 4.25bpw EXL2 Benchmarks

LLME Score: 0.15051
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dbrx Instruct 4.25bpw EXL2 (ek826/dbrx-instruct-4.25bpw-exl2)
🌟 Advertise your project 🚀

Dbrx Instruct 4.25bpw EXL2 Parameters and Internals

Model Type 
transformer-based, decoder-only, large language model, instruction fine-tuned
Use Cases 
Areas:
research, commercial applications
Applications:
natural language tasks, coding tasks
Primary Use Cases:
few-turn question answering
Limitations:
not suitable for non-English languages, does not support native code execution
Considerations:
Review associated risks; follow acceptable use policy.
Supported Languages 
primary_language (English), proficiency_level (High)
Training Details 
Data Sources:
text, code
Data Volume:
12T tokens
Methodology:
curriculum learning
Context Length:
32768
Model Architecture:
Mixture-of-Experts (MoE) with rotary position encodings, gated linear units, and grouped query attention. 16 experts, 4 chosen per input.
Input Output 
Input Format:
text-based inputs
Accepted Modalities:
text
Output Format:
text-based outputs
Release Notes 
Version:
1.0
Notes:
Initial release of DBRX Instruct, instruction fine-tuned model.
LLM NameDbrx Instruct 4.25bpw EXL2
Repository 🤗https://huggingface.co/ek826/dbrx-instruct-4.25bpw-exl2 
Required VRAM71.1 GB
Updated2025-08-18
Maintainerek826
Model Typedbrx
Instruction-BasedYes
Model Files  8.6 GB: 1-of-9   8.6 GB: 2-of-9   8.6 GB: 3-of-9   8.6 GB: 4-of-9   8.6 GB: 5-of-9   8.6 GB: 6-of-9   8.6 GB: 7-of-9   8.6 GB: 8-of-9   2.3 GB: 9-of-9
Quantization Typeexl2
Model ArchitectureDbrxForCausalLM
Licenseother
Transformers Version4.38.2
Tokenizer ClassTiktokenTokenizerWrapper
Padding Token<|pad|>
Vocabulary Size100352
Torch Data Typebfloat16
Errorsreplace

Rank the Dbrx Instruct 4.25bpw EXL2 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? 50738 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