{
  "_name_or_path": "/home/matthias/phd/artificial_tasks/meta_adapters/models/w_fsts_pretrain_s4_32_hf_ft",
  "architectures": [
    "SIPFinetuningModel"
  ],
  "auto_map": {
    "AutoModel": "modeling_sip_finetune.SIPFinetuningModel",
    "AutoModelForSeq2SeqLM": "configuration_sip_finetune.SIPFinetuningModelConfig"
  },
  "classifier_dropout": 0.0,
  "d_ff": 3584,
  "d_kv": 64,
  "d_model": 1472,
  "decoder_start_token_id": 0,
  "dense_act_fn": "gelu_new",
  "dropout_rate": 0.1,
  "eos_token_id": 1,
  "feed_forward_proj": "gated-gelu",
  "gradient_checkpointing": false,
  "initializer_factor": 1.0,
  "is_encoder_decoder": true,
  "is_gated_act": true,
  "layer_norm_epsilon": 1e-06,
  "model_type": "sip_finetune",
  "num_decoder_layers": 4,
  "num_examples": 32,
  "num_heads": 6,
  "num_layers": 12,
  "num_precomputed_examples": 400,
  "pad_token_id": 0,
  "prefix_length": 50,
  "prefix_max_init_length": 70,
  "random_selection": true,
  "relative_attention_max_distance": 128,
  "relative_attention_num_buckets": 32,
  "tie_word_embeddings": false,
  "tokenizer_class": "ByT5Tokenizer",
  "torch_dtype": "float32",
  "transformers_version": "4.38.1",
  "use_cache": true,
  "vocab_size": 384
}