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

Qwen1.5 7B Dutch Chat by robinsmits

 »  All LLMs  »  robinsmits  »  Qwen1.5 7B Dutch Chat   URL Share it on

  116   

Qwen1.5 7B Dutch Chat is an open-source language model by robinsmits. Features: 7b LLM, VRAM: 15.4GB, Context: 32K, License: cc-by-nc-4.0, HF Score: 53.7, LLM Explorer Score: 0.16, Arc: 53.9, HellaSwag: 76, MMLU: 62.4, TruthfulQA: 45.3, WinoGrande: 68.8, GSM8K: 15.5.

  Arxiv:2309.16609   Conversational Dataset:bramvanroy/ultra feedb...   Dpo   Model-index   Nl   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/robinsmits/Qwen1.5-7B-Dutch-Chat 

Qwen1.5 7B Dutch Chat Benchmarks

ARC: 53.92 vs 96.7 (so35)-44.2%
HellaSwag: 76.03 vs 95.3 (gpt4)-20.2%
MMLU: 62.38 vs 88.3 (so35)-29.4%
TruthfulQA: 45.34 vs 59 (gpt4)-23.2%
WinoGrande: 68.82 vs 87.5 (gpt4)-21.3%
GSM8K: 15.47 vs 96.4 (so35)-84%
LLME Score: 0.15518
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen1.5 7B Dutch Chat (robinsmits/Qwen1.5-7B-Dutch-Chat)
🌟 Advertise your project 🚀

Qwen1.5 7B Dutch Chat Parameters and Internals

Model Type 
text-generation
Additional Notes 
This model achieves a score very close to the performance of GPT-3.5 for Dutch tasks. Considerations are made for potential bias and hallucinations, and its non-commercial usage note must be considered.
Supported Languages 
language (Dutch), proficiency (Near GPT-3.5 Performance in Dutch Natural Language Understanding and Generation)
Training Details 
Data Sources:
BramVanroy/ultra_feedback_dutch_cleaned
Methodology:
DPO Finetuning
Training Time:
4 hours
Hardware Used:
Google Colab PRO on a A100 - 40GB
Input Output 
Input Format:
JSON-like format for chat with role and content.
Accepted Modalities:
text
Output Format:
Text generation
LLM NameQwen1.5 7B Dutch Chat
Repository 🤗https://huggingface.co/robinsmits/Qwen1.5-7B-Dutch-Chat 
Model Size7b
Required VRAM15.4 GB
Updated2026-03-29
Maintainerrobinsmits
Model Typeqwen2
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.2 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesnl
Model ArchitectureQwen2ForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|im_end|>
Vocabulary Size151646
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen1.5 7B Dutch Chat

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Preview986K / 15.2 GB50
Qwen2.5 7B Instruct 1M986K / 15.4 GB107707362
Hush Qwen2.5 7B V1.2986K / 15.2 GB31
Hush Qwen2.5 7B V1.1986K / 15.2 GB41
Hush Qwen2.5 7B V1.4986K / 15.2 GB41
Hush Qwen2.5 7B Preview986K / 15.2 GB50
Hush Qwen2.5 7B V1.3986K / 15.2 GB42
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB42
Qwen 2.5 7B Exp Sce986K / 15.2 GB42
Qwen2.5 7B MixStock V0.1986K / 15.2 GB73
Note: green Score (e.g. "73.2") means that the model is better than robinsmits/Qwen1.5-7B-Dutch-Chat.

Rank the Qwen1.5 7B Dutch Chat 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? 52509 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer