Slovak GPT J 162M by Milos

 ยป  All LLMs  ยป  Milos  ยป  Slovak GPT J 162M   URL Share it on

  Arxiv:2104.09864   Autotrain compatible   Endpoints compatible   Gptj   Pytorch   Region:us   Sk   Slovak gpt-j
Model Card on HF ๐Ÿค—: https://huggingface.co/Milos/slovak-gpt-j-162M 

Slovak GPT J 162M Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Slovak GPT J 162M (Milos/slovak-gpt-j-162M)
๐ŸŒŸ Advertise your project ๐Ÿš€

Slovak GPT J 162M Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
text generation
Limitations:
limited to 162M parameters, may generate sensitive content
Considerations:
The model may contain Czech text unintentionally.
Additional Notes 
Model trained predominantly on Slovak text corpus.
Supported Languages 
Slovak (predominantly)
Training Details 
Data Sources:
web, news articles, biblical texts
Data Volume:
40GB
Methodology:
Cross-entropy validation
Context Length:
2048
Training Time:
37 billion tokens over 69,001 steps
Hardware Used:
TPU v3-8 pod
Input Output 
Input Format:
ByteLevelBPETokenizer
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Always use US English quotation marks and double newline for new lines.
LLM NameSlovak GPT J 162M
Repository ๐Ÿค—https://huggingface.co/Milos/slovak-gpt-j-162M 
Model Size162m
Required VRAM0.3 GB
Updated2025-09-23
MaintainerMilos
Model Typegptj
Model Files  0.3 GB
Supported Languagessk
Model ArchitectureGPTJForCausalLM
Licensegpl-3.0
Transformers Version4.10.0.dev0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size50256
Torch Data Typefloat16
Activation Functiongelu_new

Best Alternatives to Slovak GPT J 162M

Best Alternatives
Context / RAM
Downloads
Likes
Gptj 162M0K / 0.3 GB3731
Note: green Score (e.g. "73.2") means that the model is better than Milos/slovak-gpt-j-162M.

Rank the Slovak GPT J 162M 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? 51540 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124