seed: 0
output_dir: './output' # path to save checkpoint/strategy
load_checkpoint: ''
use_parallel: False
run_mode: 'predict'
use_legacy: False
load_ckpt_format: 'safetensors'

trainer:
  type: CausalLanguageModelingTrainer
  model_name: 'glm4_moe'

# default parallel of device num = 8 for Atlas 800T A2
parallel_config:
  data_parallel: 1
  model_parallel: 8
# HuggingFace file directory
pretrained_model_dir: '/path/hf_dir'
model:
  model_config:
    compute_dtype: "bfloat16"
    layernorm_compute_dtype: "float32"
    softmax_compute_dtype: "float32"
    rotary_dtype: "bfloat16"
    params_dtype: "bfloat16"

# mindspore context init config
context:
  mode: 0 #0--Graph Mode; 1--Pynative Mode
  enable_graph_kernel: False
  ascend_config:
    precision_mode: "must_keep_origin_dtype"
  max_device_memory: "59GB"
  save_graphs: False
  save_graphs_path: "./graph"

# parallel context config
parallel:
  parallel_mode: "MANUAL_PARALLEL"
  enable_alltoall: False