ExpertFlowPredictor
/

predictor_all_datasets_deepseek-moe-16b-chat_moe_patterns

Upload model

9b23eb2 verified 12 months ago

142 Bytes

{
  "_from_model_config": true,
  "decoder_start_token_id": 0,
  "eos_token_id": 1,
  "pad_token_id": 0,
  "transformers_version": "4.56.2"
}