gpt-2-experimental / README.md
ahmet1338's picture
Readme file updated
611fa00
|
raw
history blame
1.49 kB
metadata
language: tr
tags:
  - turkish
  - tr
  - gpt2-tr
  - gpt2-turkish
license: mit
metrics:
  - accuracy

🇹🇷 Turkish GPT-2 Model

In this repository I release GPT-2 model, that was trained on various texts for Turkish.

The model is meant to be an entry point for fine-tuning on other texts.

Training corpora

I used a Turkish corpus that is taken from different written and oral sources.

With the Tokenizers library, I created a 52K BPE vocab based on the training corpus.

After creating the vocab, I could train the GPT-2 for Turkish on over the complete training corpus (five epochs).

Logs during training: https://tensorboard.dev/experiment/3AWKv8bBTaqcqZP5frtGkw/#scalars

Using the model

The model itself can be used in this way:

from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained("ahmet1338/gpt2-turkish-cased")
model = AutoModelWithLMHead.from_pretrained("ahmet1338/gpt2-turkish-cased")

Here's an example that shows how to use the great Transformers Pipelines for generating text:

from transformers import pipeline
pipe = pipeline('text-generation', model="ahmet1338/gpt2-turkish-cased",
                 tokenizer="ahmet1338/gpt2-turkish-cased", config={'max_length':800})   
text = pipe("Akşamüstü yolda ilerlerken, ")[0]["generated_text"]
print(text)

How to clone the model repo?

git lfs install
git clone https://huggingface.co/ahmet1338/gpt2-turkish-cased