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

Llama 2 13B Chat Dutch GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Llama 2 13B Chat Dutch GPTQ   URL Share it on

  7   
  4-bit   Adapters   Autotrain compatible Base model:adapter:bramvanroy/... Base model:bramvanroy/llama-2-...   Conversational Dataset:bramvanroy/dutch chat ...   Generated from trainer   Gptq   Llama   Lora   Nl   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Llama-2-13B-Chat-Dutch-GPTQ 

Llama 2 13B Chat Dutch GPTQ Benchmarks

LLME Score: 0.10808
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 13B Chat Dutch GPTQ (TheBloke/Llama-2-13B-Chat-Dutch-GPTQ)
🌟 Advertise your project 🚀

Llama 2 13B Chat Dutch GPTQ Parameters and Internals

Model Type 
llama, text_generation
Use Cases 
Areas:
Dutch conversational tasks, Programming assistance
Applications:
Conversational AI, Chatbot development
Primary Use Cases:
Dutch language applications
Limitations:
May produce unexpected or offensive content. Not trained on human feedback., Not suitable for competitive product development due to source data characteristics.
Considerations:
Ensure usage aligns with ethical guidelines.
Additional Notes 
Quantized versions vary in inference quality and VRAM usage.
Supported Languages 
Dutch (High proficiency)
Training Details 
Data Sources:
BramVanroy/dutch_chat_datasets, BramVanroy/dolly-15k-dutch, BramVanroy/alpaca-cleaned-dutch-baize, BramVanroy/stackoverflow-chat-dutch, BramVanroy/quora-chat-dutch
Data Volume:
4096 tokens context length
Methodology:
fine-tuned version of BramVanroy/llama2-13b-ft-mc4_nl_cleaned_tiny
Context Length:
4096
Training Time:
2 epochs
Hardware Used:
Multi-GPU (4 devices)
Model Architecture:
CLM with LoRA targeting q_proj and v_proj in 4 bit, merged before upload.
Input Output 
Input Format:
Text input formatted with prompt template.
Accepted Modalities:
Text
Output Format:
Text generation
Performance Tips:
Follow prompt guidance to ensure unbiased and helpful responses.
Release Notes 
Notes:
Fine-tuned on Dutch conversational data. Quantizations available for different hardware.
LLM NameLlama 2 13B Chat Dutch GPTQ
Repository 🤗https://huggingface.co/TheBloke/Llama-2-13B-Chat-Dutch-GPTQ 
Model CreatorBram Vanroy
Base Model(s)  Llama 2 13B Chat Dutch   BramVanroy/Llama-2-13b-chat-dutch
Model Size13b
Required VRAM7.3 GB
Updated2025-09-23
MaintainerTheBloke
Model Typellama
Model Files  7.3 GB
Supported Languagesnl
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-sa-4.0
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Llama 2 13B Chat Dutch GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K GPTQ128K / 7.3 GB1016
LongAlign 13B 64K GPTQ64K / 7.3 GB61
...boros L2 13B 2 1 YaRN 64K GPTQ64K / 7.3 GB193
Yarn Llama 2 13B 64K GPTQ64K / 7.3 GB121
OrcaMaid V3 13B 32K GPTQ32K / 7.3 GB63
OrcaMaid V2 FIX 13B 32K GPTQ32K / 7.3 GB64
EverythingLM 13B 16K GPTQ16K / 7.3 GB1414
LlongOrca 13B 16K GPT16K / 7.3 GB70
Tinybra 13B GPTQ 32g 4BIT16K / 8 GB61
Tinybra 13B GPTQ 4BIT16K / 7 GB60
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama-2-13B-Chat-Dutch-GPTQ.

Rank the Llama 2 13B Chat Dutch GPTQ 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? 51535 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