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

Fietje 2 Instruct by BramVanroy

 »  All LLMs  »  BramVanroy  »  Fietje 2 Instruct   URL Share it on

  568   
  Arxiv:2412.15450   Alignment-handbook   Autotrain compatible   Base model:bramvanroy/fietje-2 Base model:finetune:bramvanroy...   Conversational Dataset:bramvanroy/belebele du... Dataset:bramvanroy/no robots d... Dataset:bramvanroy/ultrachat 2...   Fietje   Instruct   Nl   Phi   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/BramVanroy/fietje-2-instruct 

Fietje 2 Instruct Benchmarks

MMLU Pro: 12.26
MUSR: 2.91
BBH: 17.57
IFEval: 27.9 vs 88 (so35)-68.3%
MATH Lvl 5: 0.53
LLME Score: 0.23482
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Fietje 2 Instruct (BramVanroy/fietje-2-instruct)

Fietje 2 Instruct Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Research, Commercial Applications
Limitations:
LLMs hallucinate, make mistakes, and should not be trusted. Use at your own risk!
Considerations:
Same limitations as phi-2 and LLMs in general.
Additional Notes 
Training was supported by the Flemish Supercomputer Center.
Supported Languages 
nl (Dutch)
Training Details 
Data Sources:
BramVanroy/ultrachat_200k_dutch, BramVanroy/no_robots_dutch, BramVanroy/belebele_dutch
Data Volume:
28 billion tokens
Methodology:
SFT-tuning (instruction tuning)
Training Time:
around a day
Hardware Used:
4 nodes with 4x A100 80GB GPUs each (16 total)
Model Architecture:
Derived from microsoft/phi-2
Input Output 
Accepted Modalities:
text
Output Format:
text
LLM NameFietje 2 Instruct
Repository 🤗https://huggingface.co/BramVanroy/fietje-2-instruct 
Base Model(s)  Fietje 2   BramVanroy/fietje-2
Model Size2b
Required VRAM5.6 GB
Updated2025-01-02
MaintainerBramVanroy
Model Typephi
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   0.6 GB: 2-of-2
Supported Languagesnl
Model ArchitecturePhiForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Transformers Version4.39.1
Tokenizer ClassCodeGenTokenizer
Padding Token<|im_end|>
Vocabulary Size50297
Torch Data Typebfloat16

Best Alternatives to Fietje 2 Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Fietje 2 Chat2K / 5.6 GB7431
Note: green Score (e.g. "73.2") means that the model is better than BramVanroy/fietje-2-instruct.

Rank the Fietje 2 Instruct 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? 40769 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 v20241227
  Support LLM Explorer