A small GPT2 (
lvwerra/gpt2-imdb
) language model fine-tuned to produce controlled movie reviews based the
IMDB dataset
. The model is trained with rewards from a BERT sentiment classifier (
lvwerra/bert-imdb
) via PPO.
Training setting
The model was trained for
200
optimisation steps with a batch size of
256
which corresponds to
51200
training samples. The full experiment setup can be found in the Jupyter notebook in the
trl repo
. The strings
"[negative]"
,
"[neutral]"
, and
"[positive]"
are added at the beginning of the query to control the sentiment.
Examples
A few examples of the model response to a query before and after optimisation:
query
response [negative]
rewards [negative]
response [neutral]
rewards [neutral]
response [positive]
rewards [positive]
I watched this movie when
it was released and was awful. Little bit of ...
3.130034
it was released and it was the first movie I ...
-1.351991
I was younger it was wonderful. The new play ...
4.232218
I can remember seeing this
movie in 2008, and I was so disappointed...yo...
3.428725
in support groups, which I think was not as i...
0.213288
movie, and it is one of my favorite movies ev...
4.168838
This 1970 hit film has
little resonance. This movie is bad, not only...
4.241872
a bit of Rocket power.783287. It can be easil...
0.849278
the best formula for comedy and is't just jus...
4.208804
Runs of lvwerra gpt2-imdb-ctrl on huggingface.co
7
Total runs
0
24-hour runs
0
3-day runs
-4
7-day runs
-1
30-day runs
More Information About gpt2-imdb-ctrl huggingface.co Model
gpt2-imdb-ctrl huggingface.co
gpt2-imdb-ctrl huggingface.co is an AI model on huggingface.co that provides gpt2-imdb-ctrl's model effect (), which can be used instantly with this lvwerra gpt2-imdb-ctrl model. huggingface.co supports a free trial of the gpt2-imdb-ctrl model, and also provides paid use of the gpt2-imdb-ctrl. Support call gpt2-imdb-ctrl model through api, including Node.js, Python, http.
gpt2-imdb-ctrl huggingface.co is an online trial and call api platform, which integrates gpt2-imdb-ctrl's modeling effects, including api services, and provides a free online trial of gpt2-imdb-ctrl, you can try gpt2-imdb-ctrl online for free by clicking the link below.
lvwerra gpt2-imdb-ctrl online free url in huggingface.co:
gpt2-imdb-ctrl is an open source model from GitHub that offers a free installation service, and any user can find gpt2-imdb-ctrl on GitHub to install. At the same time, huggingface.co provides the effect of gpt2-imdb-ctrl install, users can directly use gpt2-imdb-ctrl installed effect in huggingface.co for debugging and trial. It also supports api for free installation.