tiny-lm / README.md
ryo0634's picture
Update README.md
808a8e8 verified
|
raw
history blame
965 Bytes
metadata
license: apache-2.0
datasets:
  - wikipedia
language:
  - ja
  - en

tiny-lm

This repository provides a tiny 16M parameters language model for debugging and testing purposes.

Trained on English and Japanese Wikipedia data.

How to use

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, set_seed
 
model = AutoModelForCausalLM.from_pretrained("sbintuitions/tiny_lm")
tokenizer = AutoTokenizer.from_pretrained("sbintuitions/tiny_lm", use_fast=False)
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
print(generator("Hello", max_length=30, do_sample=True, top_k=1000))

Model architecture

A 4-layer, 512-hidden-size transformer-based language model.

Training

The model was trained on English Wikipedia and Japanese Wikipedia to optimize a traditional language modelling objective for 25B tokens.

License

Apache License, Version 2.0