Downloads · 30 days
7
0% of all-time downloads
movie-roberta-base
thatdramebaazguy/movie-roberta-base
movie-roberta-base is a fill-mask model from thatdramebaazguy. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as cc-by-4.0.
Objective: To make a Roberta Base for the Movie Domain by using various Movie Datasets as simple text for Masked Language Modeling. This is the Movie Roberta to be used in Movie Domain applications.
All-time downloads
2.2K
Public
Repo size
2.2 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.h5655 MB · 40%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- cc-by-4.0
- Model type
- roberta
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Jul 1, 2022
- SHA
- cc2c9085
Try a prompt
Model card
From the Hugging Face model README
roberta-base for MLM
Objective: To make a Roberta Base for the Movie Domain by using various Movie Datasets as simple text for Masked Language Modeling. This is the Movie Roberta to be used in Movie Domain applications.
model_name = "thatdramebaazguy/movie-roberta-base"
pipeline(model=model_name, tokenizer=model_name, revision="v1.0", task="Fill-Mask")
Overview
Language model: roberta-base
Language: English
Downstream-task: Fill-Mask
Training data: imdb, polarity movie data, cornell_movie_dialogue, 25mlens movie names
Eval data: imdb, polarity movie data, cornell_movie_dialogue, 25mlens movie names
Infrastructure: 4x Tesla v100
Code: See example
Hyperparameters
Num examples = 4767233
Num Epochs = 2
Instantaneous batch size per device = 20
Total train batch size (w. parallel, distributed & accumulation) = 80
Gradient Accumulation steps = 1
Total optimization steps = 119182
eval_loss = 1.6153
eval_samples = 20573
perplexity = 5.0296
learning_rate=5e-05
n_gpu = 4
Performance
perplexity = 5.0296
Some of my work:
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- License
- cc-by-4.0
- Created
- Mar 2, 2022
- Updated
- Jul 1, 2022