Text Generation
PEFT
Safetensors
Turkish
xglm
Edit model card

Poet 7B Turkish

Şiir yazmak için eğitilmiş model.

Model Details

Model Description

Bu model bulabildiğim en fazla Türkçe token ile eğitilmiş olan facebook/xglm-7.5B modelinin QLora kullanılarak fine-tune edilmiş hali. Buradaki asıl amaç modelin bu denli complex bir task'ı anlama kabiletiyini test etmekti ve sonuçlar beni gayet memnun etti.

  • Developed by: Berat Çimen
  • Model type: Autoregressive Decoder-only Transformer model with 7.5B Parameters
  • Language(s) (NLP): Turkish and English
  • License: apache-2.0
  • Finetuned from model: facebook/xglm-7.5B

Framework versions

  • PEFT 0.7.1

Contact

Website: beratcimen.com

E-Mail: [email protected]

Downloads last month
7
Safetensors
Model size
7.49B params
Tensor type
FP16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for beratcmn/Poet-7B-TR

Base model

facebook/xglm-7.5B
Adapter
(3)
this model

Dataset used to train beratcmn/Poet-7B-TR