text-generation-inference/server/text_generation/models/conf/megatron_gpt_inference.yaml

inference:
  greedy: False # 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: null  # GPT nemo file path
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
prompts: # prompts for GPT inference
  - "Q: How are you?"
  - "Q: How big is the universe?"
server: False  # whether launch the API server
port: 5555 # the port number for the inference server
web_server: False # whether launch the web inference server
share: False  # whether create a public URL
username: test # user name for web client
password: test2  # password for web client