{
  "_name_or_path": "/home/xinmatrix/hexin/offloadMoE/notebooks/logs/t5-small_wmt16_mixtral8x7bInstructv0.1_token_patterns_lrhead0.001_lrbase0.001_ws0.01_bs16_seed42_dff2048_dmodel32/model_state_dict/config.json",
  "architectures": [
    "T5ForConditionalGeneration"
  ],
  "classifier_dropout": 0.0,
  "d_ff": 2048,
  "d_kv": 64,
  "d_model": 32,
  "decoder_start_token_id": 0,
  "dense_act_fn": "relu",
  "dropout_rate": 0.1,
  "eos_token_id": 1,
  "feed_forward_proj": "relu",
  "initializer_factor": 1.0,
  "is_encoder_decoder": true,
  "is_gated_act": false,
  "layer_norm_epsilon": 1e-06,
  "model_type": "t5",
  "n_positions": 512,
  "num_decoder_layers": 6,
  "num_heads": 8,
  "num_layers": 6,
  "output_past": true,
  "pad_token_id": 0,
  "relative_attention_max_distance": 128,
  "relative_attention_num_buckets": 32,
  "task_specific_params": {
    "summarization": {
      "early_stopping": true,
      "length_penalty": 2.0,
      "max_length": 200,
      "min_length": 30,
      "no_repeat_ngram_size": 3,
      "num_beams": 4,
      "prefix": "summarize: "
    },
    "translation_en_to_de": {
      "early_stopping": true,
      "max_length": 300,
      "num_beams": 4,
      "prefix": "translate English to German: "
    },
    "translation_en_to_fr": {
      "early_stopping": true,
      "max_length": 300,
      "num_beams": 4,
      "prefix": "translate English to French: "
    },
    "translation_en_to_ro": {
      "early_stopping": true,
      "max_length": 300,
      "num_beams": 4,
      "prefix": "translate English to Romanian: "
    }
  },
  "torch_dtype": "float32",
  "transformers_version": "4.45.1",
  "use_cache": false,
  "vocab_size": 32128
}