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

Gpt3 Finnish 3B Instruct by Futurice

 »  All LLMs  »  Futurice  »  Gpt3 Finnish 3B Instruct   URL Share it on

  22   
  Arxiv:1910.09700   Autotrain compatible Base model:finetune:turkunlp/g... Base model:turkunlp/gpt3-finni...   Bloom   Conversational   Dataset:turkunlp/squad v2 fi   Endpoints compatible   Fi   Instruct   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Futurice/gpt3-finnish-3B-instruct 

Gpt3 Finnish 3B Instruct Benchmarks

LLME Score: 0.1842
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gpt3 Finnish 3B Instruct (Futurice/gpt3-finnish-3B-instruct)

Gpt3 Finnish 3B Instruct Parameters and Internals

Model Type 
Bloom
Use Cases 
Areas:
RAG type Q&A in Finnish
Applications:
Text generation
Primary Use Cases:
RAG type Q&A; supply a context and ask a question about it.
Limitations:
Simple and limited selection of fine-tuning data; do not expect high quality answers
Considerations:
Recommended to continue fine-tuning with more data or newer architecture
Supported Languages 
fi (Full proficiency)
Training Details 
Data Sources:
TurkuNLP/squad_v2_fi
Data Volume:
20000 random samples
Methodology:
Supervised fine-tuning with Lora
Training Time:
5-10 hours
Hardware Used:
1 x A100
Model Architecture:
BLOOM
Input Output 
Input Format:
Expected prompt format with context
Accepted Modalities:
text
Output Format:
Text generation output
LLM NameGpt3 Finnish 3B Instruct
Repository 🤗https://huggingface.co/Futurice/gpt3-finnish-3B-instruct 
Base Model(s)  Gpt3 Finnish 3B   TurkuNLP/gpt3-finnish-3B
Model Size3b
Required VRAM12.7 GB
Updated2025-02-22
MaintainerFuturice
Model Typebloom
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   4.9 GB: 2-of-3   2.9 GB: 3-of-3
Supported Languagesfi
Model ArchitectureBloomForCausalLM
Licenseapache-2.0
Model Max Length2048
Transformers Version4.40.1
Tokenizer ClassBloomTokenizer
Padding Token<pad>
Vocabulary Size131074
Torch Data Typefloat32

Best Alternatives to Gpt3 Finnish 3B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Bloom 3B Conversational0K / 6.1 GB2522
Blossom V2 3B0K / 6 GB20670
...a English Instruction Existing0K / 3.6 GB891
...nstruction Slimorca Pretrained0K / 3.6 GB910
...nstruction Slimorca Pretrained0K / 3.6 GB880
Instruct Tuned 3B0K / 6 GB00
Note: green Score (e.g. "73.2") means that the model is better than Futurice/gpt3-finnish-3B-instruct.

Rank the Gpt3 Finnish 3B 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? 43470 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