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

Gptj 162M by architext

 »  All LLMs  »  architext  »  Gptj 162M   URL Share it on

  155   

Gptj 162M is an open-source language model by architext. Features: 162m LLM, VRAM: 0.3GB, License: apache-2.0, LLM Explorer Score: 0.03.

  Arxiv:2303.07519   Architecture   Dataset:theodoros/architext v1   Design   En   Endpoints compatible   Gptj   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/architext/gptj-162M 

Gptj 162M Benchmarks

LLME Score: 0.03213
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gptj 162M (architext/gptj-162M)
🌟 Advertise your project 🚀

Gptj 162M Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
generating residential floor plans
Limitations:
primarily limited to residential layouts, may generate semantically incorrect designs
Considerations:
These are conceptual designs and should not be used directly for construction.
Additional Notes 
The model uses a tokenization vocabulary of 50257 with a BPEs set the same as GPT-2/GPT-3.
Supported Languages 
en (English)
Training Details 
Data Sources:
the Pile, synthetically generated data
Methodology:
The model was finetuned for 1.25 billion tokens over 11,500 steps on TPU v3-8, as an autoregressive language model, using cross-entropy loss.
Hardware Used:
TPU v3-8
Model Architecture:
Transformer model with 12 layers, model dimension of 768, and feedforward dimension of 2048, split into 16 heads with a dimension of 256 each. Rotary Position Embedding (RoPE) is applied to 64 dimensions of each head.
LLM NameGptj 162M
Repository 🤗https://huggingface.co/architext/gptj-162M 
Model Size162m
Required VRAM0.3 GB
Updated2026-03-20
Maintainerarchitext
Model Typegptj
Model Files  0.3 GB
Supported Languagesen
Model ArchitectureGPTJForCausalLM
Licenseapache-2.0
Model Max Length2048
Transformers Version4.22.2
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token<|endoftext|>
End of Sentence Token<|endoftext|>
Unk Token<|endoftext|>
Vocabulary Size50400
Torch Data Typefloat16
Activation Functiongelu_new
Errorsreplace

Best Alternatives to Gptj 162M

Best Alternatives
Context / RAM
Downloads
Likes
Slovak GPT J 162M0K / 0.3 GB8452

Rank the Gptj 162M 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? 52473 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer