Persian GPT - 110M parameters, trained from scratch

A decoder-only transformer language model trained entirely from scratch on Persian Wikipedia text. No pretrained weights, no pretrained tokenizer, no distillation β€” the model, the tokenizer, and the training corpus were all built for this project.

Model summary

Property Value
Parameters 110.4M
Architecture Decoder-only transformer (GPT-style)
Layers 12
Hidden size 768
Attention heads 12
FFN size 3072
Context length 1024
Vocabulary 32,000 (BPE, trained from scratch)
Positional encoding Learned absolute
Normalization Pre-LayerNorm
Activation GELU
Weight tying Yes
Precision fp16

Evaluation

Model Test perplexity
Unigram (add-1) 1590.26
5-gram (interpolated) 171.60
This model 14.52

11.8x improvement over the 5-gram baseline. Best val loss: 2.6391. Test loss: 2.6756.

Training details

  • Corpus: Persian Wikipedia (cleaned) β€” 855,724 documents, 244M tokens
  • Tokenizer: 32,000-token BPE trained from scratch, ZWNJ preserved
  • Hardware: Google Colab Pro, NVIDIA A100 80GB
  • Optimizer: AdamW (beta1=0.9, beta2=0.95, weight decay 0.1)
  • LR schedule: Linear warmup (500 steps) + cosine decay to 10% of peak
  • Peak LR: 3e-4
  • Effective batch: 64 (32 x 2 accumulation)
  • Epochs: 2 (7,450 optimizer steps)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
    "aradmanamnaoon/persian-lm-from-scratch",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(
    "aradmanamnaoon/persian-lm-from-scratch",
    trust_remote_code=True,
)

Limitations

  • Register: trained only on Wikipedia β€” produces encyclopedic prose, not conversational Persian.
  • Factual accuracy: no grounding mechanism. Do not use for factual QA.
  • Scale: 244M tokens for 110M params. Larger models will outperform this one.
  • License: inherits CC-BY-SA-3.0 from the training data.

The safetensors file is updated and it is a slightly better version

Citation

@misc{persian_gpt_110m, title = {Persian GPT - 110M parameters, trained from scratch}, author = {Arad Manamnaoon}, year = {2026}, url = {https://huggingface.co/aradmanamnaoon/persian-lm-from-scratch} }

Downloads last month
57
Safetensors
Model size
0.1B params
Tensor type
F16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Dataset used to train aradmanamnaoon/persian-lm-from-scratch