inference:
  greedy: True # Whether or not to use sampling ; use greedy decoding otherwise
  top_k: 0  # The number of highest probability vocabulary tokens to keep for top-k-filtering.
  top_p: 0.9 # If set to float < 1, only the most probable tokens with probabilities that add up to top_p or higher are kept for generation.
  temperature: 1.0 # sampling temperature
  add_BOS: True # add the bos token at the begining of the prompt
  tokens_to_generate: 30 # The minimum length of the sequence to be generated.
  all_probs: False  # whether return the log prob for all the tokens in vocab
  repetition_penalty: 1.2  # The parameter for repetition penalty. 1.0 means no penalty.
  min_tokens_to_generate: 0  # The minimum length of the sequence to be generated.
  compute_logprob: False  # a flag used to compute logprob of all the input text, a very special case of running inference, default False


trainer:
  devices: 1
  num_nodes: 1
  accelerator: gpu
  logger: False # logger provided by exp_manager
  precision: 16 # 16, 32, or bf16

tensor_model_parallel_size: 1
pipeline_model_parallel_size: 1
pipeline_model_parallel_split_rank: 0 # used for encoder and decoder model
gpt_model_file: ??? # GPT nemo file path # used when starting from a .nemo file
adapter_model_file: ??? # .nemo file saved during training (using megatron_gpt_adapter_tuning.py)
pred_file_path: null # save predictions to this file
checkpoint_dir: null # checkpoint file dir. This is used to load the PTL checkpoint generated during the GPT training
checkpoint_name: null # PTL checkpoint file name, only used for PTL checkpoint loading
hparams_file: null # model configuration file, only used for PTL checkpoint loading
data_paths: ??? # prompts for GPT inference
server: False  # whether launch the inference server
port: 5555 # the port number for the inference server
batch_size: 8 
num_workers: 8