LLM EXPLORER 58,297 MODELS INDEXED

Mega Ar Large 2048 Simplewiki by pszemraj

By pszemraj · 13 downloads

Mega Ar Large 2048 Simplewiki is an open-source language model by pszemraj. Features: 216.3m LLM, VRAM: 0.9GB, License: apache-2.0, LLM Explorer Score: 0.09.

Dataset:pszemraj/simple wikipe...   Endpoints compatible   Generated from trainer   Mega   Pytorch   Region:us   Safetensors

Mega Ar Large 2048 Simplewiki Parameters and Internals

Model Type 
autoregressive, text-generation
Additional Notes 
This model was trained from random weights and trained for three epochs using Simple Wikipedia.
Training Details 
Data Sources:
pszemraj/simple_wikipedia_LM
LLM NameMega Ar Large 2048 Simplewiki
Repository πŸ€—https://huggingface.co/pszemraj/mega-ar-large-2048-simplewiki 
Base Model(s)  pszemraj/random-mega-ar-large   pszemraj/random-mega-ar-large
Model Size216.3m
Required VRAM0.9 GB
Updated2026-08-07
Maintainerpszemraj
Model Typemega
Model Files  0.9 GB   0.9 GB   0.0 GB
Model ArchitectureMegaForCausalLM
Licenseapache-2.0
Model Max Length2048
Transformers Version4.33.1
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50277
Torch Data Typefloat32