Downloads · 30 days
575
22% of all-time downloads
gpt2-urdu-news
Imran1/gpt2-urdu-news
gpt2-urdu-news is a text generation model from Imran1. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
Fine tune gpt2 model on Urdu news dataset using a causal language modeling (CLM) objective.
All-time downloads
2.6K
Public
Parameters
175M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin663 MB · 50%
Parameter types
How the weights are stored.
F32163M · 93%
Datasets
Model card
From the Hugging Face model README
GPT-2
Fine tune gpt2 model on Urdu news dataset using a causal language modeling (CLM) objective.
How to use
You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we set a seed for reproducibility:
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Imran1/gpt2-urdu-news")
model = AutoModelForCausalLM.from_pretrained("Imran1/gpt2-urdu-news")
Training data
I fine tune gpt2 for downstream task like text generation, only for 1000 sample so it may not be good. Due to resources limitation.
Evaluation results
training loss 3.042
- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- License
- mit
- Languages
- ur
- Created
- Sep 30, 2022
- Updated
- Apr 7, 2023