config.json

{
  "adapters": {
    "adapters": {
      "heavy2light_adapter": "dcb52aee526a3537"
    },
    "config_map": {
      "dcb52aee526a3537": {
        "adapter_residual_before_ln": false,
        "cross_adapter": false,
        "dropout": 0.0,
        "factorized_phm_W": true,
        "factorized_phm_rule": false,
        "hypercomplex_nonlinearity": "glorot-uniform",
        "init_weights": "bert",
        "inv_adapter": null,
        "inv_adapter_reduction_factor": null,
        "is_parallel": false,
        "learn_phm": true,
        "leave_out": [],
        "ln_after": false,
        "ln_before": false,
        "mh_adapter": true,
        "non_linearity": "relu",
        "original_ln_after": true,
        "original_ln_before": false,
        "output_adapter": true,
        "phm_bias": true,
        "phm_c_init": "normal",
        "phm_dim": 4,
        "phm_init_range": 0.0001,
        "phm_layer": false,
        "phm_rank": 1,
        "reduction_factor": 16,
        "residual_before_ln": true,
        "scaling": 1.0,
        "shared_W_phm": false,
        "shared_phm_rule": true,
        "use_gating": false
      }
    },
    "fusion_config_map": {},
    "fusions": {}
  },
  "add_cross_attention": true,
  "architectures": [
    "EncoderDecoderModelWithAdapters"
  ],
  "bos_token_id": 2,
  "decoder": {
    "_name_or_path": "/ibmm_data2/oas_database/paired_lea_tmp/light_model/gpt_model_light_unpaired/src/gpt_light_model_unpaired/model_outputs/full_new_tokenizer_gpt2_light_seqs_unp_lr_5e-4_wd_0.1_bs_32_epochs_500_/checkpoint-6058816",
    "activation_function": "gelu_new",
    "add_cross_attention": true,
    "architectures": [
      "GPT2LMHeadModel"
    ],
    "attn_pdrop": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "embd_pdrop": 0.1,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 0,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "is_decoder": true,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_epsilon": 1e-05,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "gpt2",
    "n_ctx": 1024,
    "n_embd": 768,
    "n_head": 12,
    "n_inner": null,
    "n_layer": 12,
    "n_positions": 1024,
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 1,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "reorder_and_upcast_attn": false,
    "repetition_penalty": 1.0,
    "resid_pdrop": 0.1,
    "return_dict": true,
    "return_dict_in_generate": false,
    "scale_attn_by_inverse_layer_idx": false,
    "scale_attn_weights": true,
    "sep_token_id": null,
    "summary_activation": null,
    "summary_first_dropout": 0.1,
    "summary_proj_to_labels": true,
    "summary_type": "cls_index",
    "summary_use_proj": true,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "float32",
    "torchscript": false,
    "typical_p": 1.0,
    "unk_token_id": 2,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 25
  },
  "decoder_start_token_id": 2,
  "encoder": {
    "_name_or_path": "/ibmm_data2/oas_database/paired_lea_tmp/heavy_model/src/redo_ch/FULL_config_4_smaller_model_run_lr5e-5_500epochs_max_seq_length_512/checkpoint-117674391",
    "add_cross_attention": false,
    "architectures": [
      "RobertaForMaskedLM"
    ],
    "attention_probs_dropout_prob": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "classifier_dropout": null,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 512,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 2048,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "length_penalty": 1.0,
    "max_length": 512,
    "max_position_embeddings": 514,
    "max_seq_length": 512,
    "min_length": 0,
    "model_type": "roberta",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 4,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 4,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 1,
    "position_embedding_type": "absolute",
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "float32",
    "torchscript": false,
    "type_vocab_size": 1,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 25
  },
  "eos_token_id": 3,
  "is_encoder_decoder": true,
  "mask_token": null,
  "model_type": "encoder-decoder",
  "pad_token_id": 0,
  "torch_dtype": "float32",
  "transformers_version": "4.40.2"
}