APT3 1B Base by Azurro

 ยป  All LLMs  ยป  Azurro  ยป  APT3 1B Base   URL Share it on

  Allamo   Autotrain compatible Dataset:chrisociepa/wikipedia-...   Llama   Pl   Region:us   Safetensors
Model Card on HF ๐Ÿค—: https://huggingface.co/Azurro/APT3-1B-Base 

APT3 1B Base Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
APT3 1B Base (Azurro/APT3-1B-Base)

APT3 1B Base Parameters and Internals

Model Type 
causal decoder-only
Use Cases 
Areas:
research, scientific purposes
Limitations:
Not intended for deployment without fine-tuning, May produce factually incorrect or offensive content
Supported Languages 
Polish (fluent)
Training Details 
Data Sources:
Speakleash, Polish Wikipedia, Publicly available and crawled web data
Data Volume:
285GB of text corpus
Context Length:
2048
Hardware Used:
Nvidia RTX 4090 24GB VRAM
Model Architecture:
autoregressive, transformer-based
Input Output 
Performance Tips:
Use Hugging Face Pipelines and smaller precision (bfloat16) to reduce memory usage.
LLM NameAPT3 1B Base
Repository ๐Ÿค—https://huggingface.co/Azurro/APT3-1B-Base 
Model Size1b
Required VRAM4.2 GB
Updated2025-02-15
MaintainerAzurro
Model Typellama
Model Files  0.0 GB   4.2 GB   8.3 GB   4.2 GB
Supported Languagespl
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length2048
Model Max Length2048
Transformers Version4.35.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size31980
Torch Data Typefloat32

Best Alternatives to APT3 1B Base

Best Alternatives
Context / RAM
Downloads
Likes
LWM Text Chat 1M1024K / 13.5 GB1418175
LWM Text 1M1024K / 13.5 GB33728
JOSIE 1M Base1024K / 13.5 GB121
JOSIE 1M Base1024K / 13.5 GB61
Llama 3.2 1B128K / 2.5 GB104805291561
Llama 3.2 1B Instruct128K / 2.5 GB1678671755
Llama 3.2 1B Instruct128K / 2.5 GB13477463
MiniThinky V2 1B Llama 3.2128K / 4.9 GB1245338
Orca Mini V9 6 1B Instruct128K / 2.5 GB5364
Llama Express.1 Math128K / 2.5 GB1577
Note: green Score (e.g. "73.2") means that the model is better than Azurro/APT3-1B-Base.

Rank the APT3 1B Base Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 43186 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227