checkpoint-10500/config.json

{
  "K": 4096,
  "architectures": [
    "MomentumDualEncoderModel"
  ],
  "assembly_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": [
      "LongelmForMaskedLMWithEdgePrediction"
    ],
    "attention_probs_dropout_prob": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "block_size": 8,
    "bos_token_id": 1,
    "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,
    "ep_add_linear_projection": true,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "global_memory_size": 1,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 768,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-12,
    "length_penalty": 1.0,
    "max_blocks": 200,
    "max_length": 20,
    "max_position_embeddings": 1805,
    "max_relative_position_embeddings": 8,
    "min_length": 0,
    "model_type": "longelm",
    "no_repeat_ngram_size": 0,
    "node_size": 1,
    "num_attention_heads": 12,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 3,
    "position_embedding_type": "mixed",
    "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": 2,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 50265
  },
  "logit_scale_init_value": 2.6592,
  "m": 0.999,
  "model_type": "assembly-source-dual-encoder",
  "projection_dim": 512,
  "source_config": {
    "_name_or_path": "Salesforce/codet5p-110m-embedding",
    "add_cross_attention": false,
    "architectures": [
      "CodeT5p_Embedding"
    ],
    "auto_map": {
      "AutoConfig": "Salesforce/codet5p-110m-embedding--configuration_codet5p_embedding.CodeT5pEmbeddingConfig",
      "AutoModel": "Salesforce/codet5p-110m-embedding--modeling_codet5p_embedding.CodeT5pEmbeddingModel"
    },
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 1,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "d_ff": 3072,
    "d_kv": 64,
    "d_model": 768,
    "decoder_start_token_id": 0,
    "dense_act_fn": "relu",
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout_rate": 0.1,
    "early_stopping": false,
    "embed_dim": 256,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "feed_forward_proj": "relu",
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "gradient_checkpointing": false,
    "id2label": {
      "0": "LABEL_0"
    },
    "initializer_factor": 1.0,
    "is_decoder": false,
    "is_encoder_decoder": true,
    "is_gated_act": false,
    "label2id": {
      "LABEL_0": 0
    },
    "layer_norm_epsilon": 1e-06,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "codet5p_embedding",
    "n_positions": 512,
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_heads": 12,
    "num_layers": 12,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_past": true,
    "output_scores": false,
    "pad_token_id": 0,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "relative_attention_max_distance": 128,
    "relative_attention_num_buckets": 32,
    "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,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": false,
    "vocab_size": 32103
  },
  "torch_dtype": "float32",
  "transformers_version": "4.39.3"
}