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

Qwen1.5 7B Dutch Chat Sft Bf16 by robinsmits

 »  All LLMs  »  robinsmits  »  Qwen1.5 7B Dutch Chat Sft Bf16   URL Share it on

  5   
  Arxiv:2309.16609   Autotrain compatible   Conversational Dataset:bramvanroy/ultrachat 2...   Nl   Qwen2   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/robinsmits/Qwen1.5-7B-Dutch-Chat-Sft-Bf16 

Qwen1.5 7B Dutch Chat Sft Bf16 Benchmarks

ARC: 54.27 vs 96.7 (so35)-43.9%
HellaSwag: 75.53 vs 95.3 (gpt4)-20.7%
MMLU: 61.98 vs 88.3 (so35)-29.8%
TruthfulQA: 47.26 vs 59 (gpt4)-19.9%
WinoGrande: 68.67 vs 87.5 (gpt4)-21.5%
GSM8K: 21.76 vs 96.4 (so35)-77.4%
LLME Score: 0.16664
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 Sft Bf16 (robinsmits/Qwen1.5-7B-Dutch-Chat-Sft-Bf16)
🌟 Advertise your project 🚀

Qwen1.5 7B Dutch Chat Sft Bf16 Parameters and Internals

Model Type 
text-generation, conversational
Use Cases 
Areas:
research, applications with a focus on Dutch texts
Primary Use Cases:
chatbot, language understanding
Limitations:
bias, hallucinations due to undesired model behaviors
Considerations:
Ensure testing and validation
Supported Languages 
nl (native)
Training Details 
Data Sources:
BramVanroy/ultrachat_200k_dutch
Data Volume:
approximately 200k utterances
Methodology:
Fine-tuning
Training Time:
14 hours per part, split into two parts due to Google Colab PRO session limits
Hardware Used:
A100 - 40GB GPU via Google Colab PRO
Model Architecture:
Adapter model merge
Input Output 
Input Format:
chat formatted messages
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Utilize the `generate` method effectively for controlled outputs.
LLM NameQwen1.5 7B Dutch Chat Sft Bf16
Repository 🤗https://huggingface.co/robinsmits/Qwen1.5-7B-Dutch-Chat-Sft-Bf16 
Model Size7b
Required VRAM15.4 GB
Updated2025-09-23
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<|endoftext|>
Vocabulary Size151646
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen1.5 7B Dutch Chat Sft Bf16

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB169878351
Hush Qwen2.5 7B V1.2986K / 15.2 GB31
Hush Qwen2.5 7B V1.1986K / 15.2 GB31
Hush Qwen2.5 7B V1.4986K / 15.2 GB31
Hush Qwen2.5 7B Preview986K / 15.2 GB50
Hush Qwen2.5 7B V1.3986K / 15.2 GB32
Qwen2.5 7B Preview986K / 15.2 GB50
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB22
Qwen 2.5 7B Exp Sce986K / 15.2 GB22
Qwen2.5 7B MixStock V0.1986K / 15.2 GB43
Note: green Score (e.g. "73.2") means that the model is better than robinsmits/Qwen1.5-7B-Dutch-Chat-Sft-Bf16.

Rank the Qwen1.5 7B Dutch Chat Sft Bf16 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? 51545 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