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

Dbrx Base Converted V2 4bit Gptq Marlin V2 by LnL-AI

 »  All LLMs  »  LnL-AI  »  Dbrx Base Converted V2 4bit Gptq Marlin V2   URL Share it on

  4   
  Arxiv:2211.15841   Arxiv:2304.11277   4-bit   4bit   Autotrain compatible   Custom code   Dbrx   Endpoints compatible   Gptq   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin-v2 

Dbrx Base Converted V2 4bit Gptq Marlin V2 Benchmarks

LLME Score: 0.15094
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dbrx Base Converted V2 4bit Gptq Marlin V2 (LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin-v2)
🌟 Advertise your project 🚀

Dbrx Base Converted V2 4bit Gptq Marlin V2 Parameters and Internals

Model Type 
transformer-based, large language model, mixture-of-experts
Use Cases 
Areas:
commercial applications, research
Primary Use Cases:
text completion, coding tasks
Limitations:
Designed primarily for English, does not support non-English languages, Not for native code execution or function-calling
Considerations:
Use with caution for general English-language and coding tasks; additional testing recommended for safety
Additional Notes 
DBRX Base is a mixture-of-experts large language model with a fine-grained approach using 16 experts and RoPE. It is distributed under an open model license.
Supported Languages 
English (high proficiency)
Training Details 
Data Sources:
text, code
Data Volume:
12 trillion tokens
Methodology:
mixture-of-experts (MoE)
Context Length:
32768
Hardware Used:
1xA100 80G GPU
Model Architecture:
decoder-only with next-token prediction, rotary position encodings, gated linear units, grouped query attention
Input Output 
Input Format:
text-based inputs
Accepted Modalities:
text
Output Format:
text-based outputs
Performance Tips:
Use PR https://github.com/AutoGPTQ/AutoGPTQ/pull/625 and combine_tensors.sh script
LLM NameDbrx Base Converted V2 4bit Gptq Marlin V2
Repository 🤗https://huggingface.co/LnL-AI/dbrx-base-converted-v2-4bit-gptq-marlin-v2 
Updated2025-08-18
MaintainerLnL-AI
Model Typedbrx
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureDbrxForCausalLM
Licenseother
Transformers Version4.38.2
Tokenizer ClassTiktokenTokenizerWrapper
Padding Token<|endoftext|>
Vocabulary Size100352
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Dbrx Base Converted V2 4bit Gptq Marlin V2

Best Alternatives
Context / RAM
Downloads
Likes
...se Converted V2 4bit Gptq Gptq0K /  GB61
Dbrx Instruct 4.25bpw EXL20K / 71.1 GB41

Rank the Dbrx Base Converted V2 4bit Gptq Marlin V2 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? 50729 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