mirror of
https://github.com/saymrwulf/transformers.git
synced 2026-05-14 20:58:08 +00:00
Pr for pplm (#2060)
* license * changes * ok * Update paper link and commands to run * pointer to uber repo
This commit is contained in:
Rosanne Liu
Julien Chaumond
parent
bebaa14039
commit
ee53de7aac
3 changed files with 32 additions and 37 deletions
|
|
@ -1,17 +1,15 @@
|
|||
# PPLM
|
||||
# Plug and Play Language Models: a Simple Approach to Controlled Text Generation
|
||||
|
||||
Authors: [Sumanth Dathathri](https://dathath.github.io/), [Andrea Madotto](https://andreamad8.github.io/), Janice Lan, Jane Hung, Eric Frank, [Piero Molino](https://w4nderlu.st/), [Jason Yosinski](http://yosinski.com/), and [Rosanne Liu](http://www.rosanneliu.com/)
|
||||
|
||||
This folder contains the original code used to run the Plug and Play Language Model (PPLM).
|
||||
|
||||
|
||||
## Plug and Play Language Models: a Simple Approach to Steerable Text Generation
|
||||
Authors: [Sumanth Dathathri](https://dathath.github.io/), Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, [Piero Molino](https://w4nderlu.st/), [Jason Yosinski](http://yosinski.com/), and [Rosanne Liu](http://www.rosanneliu.com/)
|
||||
|
||||
PPLM allows a user to flexibly plug in one or more tiny attribute models representing the desired steering objective into a large, unconditional LM. The method has the key property that it uses the LM _as is_---no training or fine-tuning is required---which enables researchers to leverage best-in-class LMs even if they do not have the extensive hardware required to train them.
|
||||
|
||||
Paper link:
|
||||
Paper link: https://arxiv.org/abs/1912.02164
|
||||
|
||||
Blog link: https://eng.uber.com/pplm
|
||||
|
||||
Please check out the repo under uber-research for more information: https://github.com/uber-research/PPLM
|
||||
|
||||
|
||||
## Setup
|
||||
|
||||
|
|
@ -27,7 +25,7 @@ cd examples/pplm
|
|||
### Example command for bag-of-words control
|
||||
|
||||
```bash
|
||||
python run_pplm.py -B space --cond_text "The president" --length 100 --gamma 1.5 --num_iterations 3 --num_samples 1 --stepsize 0.01 --window_length 5 --kl_scale 0.01 --gm_scale 0.95
|
||||
python run_pplm.py -B military --cond_text "The potato" --length 50 --gamma 1.5 --num_iterations 3 --num_samples 10 --stepsize 0.03 --window_length 5 --kl_scale 0.01 --gm_scale 0.99 --colorama --sample
|
||||
```
|
||||
|
||||
### Tuning hyperparameters for bag-of-words control
|
||||
|
|
@ -45,7 +43,7 @@ python run_pplm.py -B space --cond_text "The president" --length 100 --gamma 1.5
|
|||
### Example command for discriminator based sentiment control
|
||||
|
||||
```bash
|
||||
python run_pplm.py -D sentiment --class_label 3 --cond_text "The lake" --length 10 --gamma 1.0 --num_iterations 10 --num_samples 1 --stepsize 0.03 --kl_scale 0.01 --gm_scale 0.95
|
||||
python run_pplm.py -D sentiment --class_label 2 --cond_text "My dog died" --length 50 --gamma 1.0 --num_iterations 10 --num_samples 10 --stepsize 0.04 --kl_scale 0.01 --gm_scale 0.95 --sample
|
||||
```
|
||||
|
||||
### Tuning hyperparameters for discriminator control
|
||||
|
|
@ -54,8 +52,3 @@ python run_pplm.py -D sentiment --class_label 3 --cond_text "The lake" --length
|
|||
|
||||
2. Use `--class_label 3` for negative, and `--class_label 2` for positive
|
||||
|
||||
### Example command for detoxificiation:
|
||||
|
||||
```bash
|
||||
python run_pplm.py -D toxicity --length 100 --num_iterations 10 --cond-text 'TH PEOPLEMan goddreams Blacks' --gamma 1.0 --num_samples 10 --stepsize 0.02
|
||||
```
|
||||
|
|
|
|||
|
|
@ -1,18 +1,19 @@
|
|||
#! /usr/bin/env python3
|
||||
# coding=utf-8
|
||||
# Copyright 2018 The Uber AI Team Authors.
|
||||
|
||||
#Copyright (c) 2019 Uber Technologies, Inc.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#Licensed under the Apache License, Version 2.0 (the "License");
|
||||
#you may not use this file except in compliance with the License.
|
||||
#You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
#Unless required by applicable law or agreed to in writing, software
|
||||
#distributed under the License is distributed on an "AS IS" BASIS,
|
||||
#WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
#See the License for the specific language governing permissions and
|
||||
#limitations under the License.
|
||||
|
||||
"""
|
||||
Example command with bag of words:
|
||||
|
|
@ -45,12 +46,9 @@ SMALL_CONST = 1e-15
|
|||
BIG_CONST = 1e10
|
||||
|
||||
BAG_OF_WORDS_ARCHIVE_MAP = {
|
||||
'kitchen': "https://s3.amazonaws.com/models.huggingface.co/bert/pplm/bow/kitchen.txt",
|
||||
'legal': "https://s3.amazonaws.com/models.huggingface.co/bert/pplm/bow/legal.txt",
|
||||
'military': "https://s3.amazonaws.com/models.huggingface.co/bert/pplm/bow/military.txt",
|
||||
'monsters': "https://s3.amazonaws.com/models.huggingface.co/bert/pplm/bow/monsters.txt",
|
||||
'politics': "https://s3.amazonaws.com/models.huggingface.co/bert/pplm/bow/politics.txt",
|
||||
'positive_words': "https://s3.amazonaws.com/models.huggingface.co/bert/pplm/bow/positive_words.txt",
|
||||
'religion': "https://s3.amazonaws.com/models.huggingface.co/bert/pplm/bow/religion.txt",
|
||||
'science': "https://s3.amazonaws.com/models.huggingface.co/bert/pplm/bow/science.txt",
|
||||
'space': "https://s3.amazonaws.com/models.huggingface.co/bert/pplm/bow/space.txt",
|
||||
|
|
@ -74,14 +72,6 @@ DISCRIMINATOR_MODELS_PARAMS = {
|
|||
"default_class": 3,
|
||||
"pretrained_model": "gpt2-medium",
|
||||
},
|
||||
"toxicity": {
|
||||
"url": "https://s3.amazonaws.com/models.huggingface.co/bert/pplm/discriminators/toxic_classifier_head.pt",
|
||||
"class_size": 2,
|
||||
"embed_size": 1024,
|
||||
"class_vocab": {"non_toxic": 0, "toxic": 1},
|
||||
"default_class": 0,
|
||||
"pretrained_model": "gpt2-medium",
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1,7 +1,19 @@
|
|||
#! /usr/bin/env python3
|
||||
# coding=utf-8
|
||||
|
||||
# This code is licensed under a non-commercial license.
|
||||
#Copyright (c) 2019 Uber Technologies, Inc.
|
||||
#
|
||||
#Licensed under the Apache License, Version 2.0 (the "License");
|
||||
#you may not use this file except in compliance with the License.
|
||||
#You may obtain a copy of the License at
|
||||
#
|
||||
#http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
#Unless required by applicable law or agreed to in writing, software
|
||||
#distributed under the License is distributed on an "AS IS" BASIS,
|
||||
#WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
#See the License for the specific language governing permissions and
|
||||
#limitations under the License.
|
||||
|
||||
import argparse
|
||||
import csv
|
||||
|
|
|
|||
Loading…
Reference in a new issue