large-gpu.cfg

###################
#     General     #
###################

[general_params]

# Device ordinal for CPU/GPU supports.
# Setting this to -1 will leverage CPU, a positive will run the model on the associated CUDA device id.
device = 0

# Seed for random number generators, fix seed to reproduce results.
# By default there is no seed and each turn should be unique.
seed

# Whether to enable debugging.
debug = False


###########################
#     Text generation     #
###########################

# DialoGPT (see https://github.com/microsoft/DialoGPT) or any other text generator supported by `transformers.pipeline`.

[generation_pipeline_kwargs]
# Keyword arguments passed to the text generation pipeline.

# The model that will be used by the pipeline 'text-generation' to generate responses.
# The model must be an instance of a pretrained model inheriting from `PreTrainedModel` or `TFPreTrainedModel`.
model = microsoft/DialoGPT-large

# The configuration that will be used by the pipeline to instantiate the model.
config

# The tokenizer that will be used by the pipeline to encode data for the model.
tokenizer

# The framework to use, either pt for PyTorch or tf for TensorFlow.
# The specified framework must be installed.
framework

[generator_kwargs]
# Keyword arguments passed to the text generator.
# See https://huggingface.co/blog/how-to-generate

# The maximal number of tokens to be returned, inclusive of punctuations etc.
# It will automatically stop if the end-of-sequence token was found earlier.
max_length = 1000

# The minimum length of the sequence to be generated.
min_length = 1

# Whether or not to use sampling; use greedy decoding otherwise.
do_sample = True

# Whether to stop the beam search when at least `num_beams` sentences are finished per batch or not.
early_stopping = False

# Number of beams for beam search.
# 1 means no beam search.
num_beams = 1

# Number of groups to divide `num_beams` into in order to ensure diversity among different groups of beams.
# 1 means no group beam search.
num_beam_groups = 1

# Value to control diversity for group beam search.
# The higher the penalty, the more diverse are the outputs.
diversity_penalty = 0.0

# The value used to module the next token probabilities.
# Must be strictly positive.
# Lower temperature results in less random completions.
# As the temperature approaches zero, the model will become deterministic and repetitive.
# Higher temperature results in more random completions.
temperature = 1

# The number of highest probability vocabulary tokens to keep for top-k-filtering.
# 1 means only 1 word is considered for each step (token), resulting in deterministic completions,
# while 40 means 40 words are considered at each step.
# 0 (default) is a special setting meaning no restrictions.
# 40 generally is a good value.
top_k = 40

# If set to float < 1, only the most probable tokens with probabilities
# that add up to top_p or higher are kept for generation.
top_p = 0.9

# The parameter for repetition penalty. 1.0 means no penalty.
repetition_penalty = 1

# Exponential penalty to the length. 1.0 means no penalty.
# Set to values < 1.0 in order to encourage the model to generate shorter sequences,
# to a value > 1.0 in order to encourage the model to produce longer sequences.
length_penalty = 1

# If set to int > 0, all ngrams of that size can only occur once.
no_repeat_ngram_size = 0

# The id of the padding token.
pad_token_id

# The id of the beginning-of-sequence token.
bos_token_id

# The id of the end-of-sequence token.
eos_token_id

# Comma separated list of token ids that are not allowed to be generated.
bad_words_ids

# The number of independently computed returned sequences for each element in the batch.
# You would need to use a response classifier or implement a function.
# For example, you can choose the most dissimilar message, or the lengthiest one.
# But keep in mind: the higher the number, the slower the generation.
num_return_sequences = 1

# If an encoder-decoder model starts decoding with a different token than bos, the id of that token.
decoder_start_token_id

# Whether or not the model should use the past last key/values attentions
# (if applicable to the model) to speed up decoding.
use_cache = True

# Whether or not to clean up the potential extra spaces in the text output.
clean_up_tokenization_spaces = True


############################
#     Response ranking     #
############################

# DialogRPT (see https://github.com/golsun/DialogRPT)
# Any ranker can be disabled by setting to empty.
# NOTE: Ensure num_return_sequences is greater than 1.

[prior_ranker_weights]
# The `prior` score is the weighted average of `human_vs_rand` and `human_vs_machine` predictions.

# Weight of "How relevant the response is for the given context?"
human_vs_rand_weight

# Weight of "How likely the response is human-written rather than machine-generated?"
human_vs_machine_weight

[cond_ranker_weights]
# The `cond` score is the weighted average of `updown`, `depth` and `width` predictions.

# Weight of "How likely the response gets the most upvotes?"
updown_weight

# Weight of "How likely the response gets the most direct replies?"
depth_weight

# Weight of "How likely the response gets the longest follow-up thread?"
width_weight


#########################
#     Communication     #
#########################

[chatbot_params]
# Parameters of the chatbot itself.

# The number of turns (turn = answer and response) the model should consider.
# Set to 0 to focus on the last message. Set to -1 for unlimited context length.
max_turns_history = 2

# Your Telegram token. See https://core.telegram.org/bots
telegram_token = YOUR_TOKEN_HERE

# Your GIPHY API token. See https://developers.giphy.com/docs/api/
giphy_token = YOUR_TOKEN_HERE

# Probability of returning a GIF.
giphy_prob = 0.1

# The maximal number of words the bot has to generate to also return a GIF.
giphy_max_words = 3

# Value from 0-10 which makes results weirder as you go up the scale.
giphy_weirdness = 5

# Whether to continue from the previous dialogue.
continue_after_restart = True

# The filename for storing the pickle files.
data_filename = bot_data.pkl