Downloads · 30 days
42
2% of all-time downloads
mrm8488/gpt2-imdb-neg
gpt2-imdb-neg is a machine learning model from mrm8488. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
Downloads · 30 days
42
2% of all-time downloads
All-time downloads
1.8K
Public
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.bin548 MB · 100%
From the Hugging Face model README
All credits to @lvwerra
A small GPT2 (lvwerra/gpt2-imdb) language model fine-tuned to produce negative movie reviews based the IMDB dataset. The model is trained with rewards from a BERT sentiment classifier (lvwerra/gpt2-imdb) via PPO.
I wanted to reproduce the experiment lvwerra/gpt2-imdb-pos but for generating negative movie reviews.
The model was trained for 100 optimisation steps with a batch size of 256 which corresponds to 25600 training samples. The full experiment setup (for positive samples) in trl repo.
A few examples of the model response to a query before and after optimisation:
| query | response (before) | response (after) | rewards (before) | rewards (after) |
|---|---|---|---|---|
| This movie is a fine | attempt as far as live action is concerned, n... | example of how bad Hollywood in theatrics pla... | 2.118391 | -3.31625 |
| I have watched 3 episodes | with this guy and he is such a talented actor... | but the show is just plain awful and there ne... | 2.681171 | -4.512792 |
| We know that firefighters and | police officers are forced to become populari... | other chains have going to get this disaster ... | 1.367811 | -3.34017 |
Watch the whole training logs and metrics on W&B
Created by Manuel Romero/@mrm8488
Made with <span style="color: #e25555;">♥</span> in Spain