Downloads · 30 days
13
0% of all-time downloads
rugpt-neo-1.3b
AlexWortega/rugpt-neo-1.3b
rugpt-neo-1.3b is a text generation model from AlexWortega. 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.
ruGPT-Neo 1.3B is a transformer model designed using EleutherAI's replication of the GPT-3 architecture. ruGPT-Neo refers to the class of models, while 1.3B represents the number of parameters of this particular pre-t…
All-time downloads
2.9K
Public
Repo size
48.3 GB
Likes
9
Public
Repo makeup
Click a slice to open those files.
.bin5.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- gpt_neo
- Access
- Public
- Created
- Jan 7, 2023
- Updated
- Jan 15, 2023
- SHA
- 1f2433e0
Datasets
Model card
From the Hugging Face model README
ruGPT-Neo 1.3B [IN TRANING, 100k/2M NOT FINAL CHECKPOINT]
Model Description
ruGPT-Neo 1.3B is a transformer model designed using EleutherAI's replication of the GPT-3 architecture. ruGPT-Neo refers to the class of models, while 1.3B represents the number of parameters of this particular pre-trained model.
Training procedure
This model was trained on the wiki, gazeta summorization, for 38k steps, on 1*v100 gpu, still training . It was trained as a masked autoregressive language model, using cross-entropy loss.
How to use
You can use this model directly with a pipeline for text generation. This example generates a different sequence each time it's run:
>>> from transformers import pipeline
>>> generator = pipeline('text-generation', model='AlexWortega/rugpt-neo-1.3b')
>>> generator("Как какать? Ответ:", do_sample=True, min_length=50)
[{'generated_text': 'Как какать? Ответ: Cпустите штаны и покакайте, затем воспользуйтесь бумагой'}]
- Task
- Text Generation
- Library
- transformers
- Type
- gpt_neo
- License
- mit
- Languages
- ru
- Created
- Jan 7, 2023
- Updated
- Jan 15, 2023