| { |
| "architectures": [ |
| "MILCOModel" |
| ], |
| "auto_map": { |
| "AutoConfig": "milco.MILCOConfig", |
| "AutoModel": "milco.MILCOModel" |
| }, |
| "dtype": "bfloat16", |
| "en_hidden_size": 768, |
| "en_sub_config": { |
| "_name_or_path": "naver/splade-v3", |
| "add_cross_attention": false, |
| "architectures": [ |
| "BertForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "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, |
| "dtype": "float32", |
| "early_stopping": false, |
| "encoder_no_repeat_ngram_size": 0, |
| "eos_token_id": null, |
| "exponential_decay_length_penalty": null, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "gradient_checkpointing": false, |
| "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_length": 20, |
| "max_position_embeddings": 512, |
| "min_length": 0, |
| "model_type": "bert", |
| "no_repeat_ngram_size": 0, |
| "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": 0, |
| "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, |
| "torchscript": false, |
| "transformers_version": "4.57.3", |
| "type_vocab_size": 2, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "vocab_size": 30522 |
| }, |
| "en_vocab_size": 30522, |
| "freeze_embeddings": false, |
| "lambda_commitment": 0.0, |
| "lambda_d": 1e-05, |
| "lambda_q": 0.001, |
| "lambda_sparsity": 0.0, |
| "lsr_encoder_checkpoint": "naver/splade-v3", |
| "m_hidden_size": 1024, |
| "m_sub_config": { |
| "_name_or_path": "BAAI/bge-m3-unsupervised", |
| "add_cross_attention": false, |
| "architectures": [ |
| "XLMRobertaModel" |
| ], |
| "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, |
| "dtype": "float32", |
| "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": 1024, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "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": 20, |
| "max_position_embeddings": 8194, |
| "min_length": 0, |
| "model_type": "xlm-roberta", |
| "no_repeat_ngram_size": 0, |
| "num_attention_heads": 16, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 24, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_past": true, |
| "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, |
| "torchscript": false, |
| "transformers_version": "4.57.3", |
| "type_vocab_size": 1, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "vocab_size": 250002 |
| }, |
| "m_vocab_size": 250002, |
| "model_type": "milco", |
| "model_variant": "bert", |
| "multilingual_encoder_checkpoint": "BAAI/bge-m3-unsupervised", |
| "only_distillation": true, |
| "pooling": "2d", |
| "projector_pretraining": false, |
| "prompt_length": 0, |
| "separate_mlp": true, |
| "softmax_temperature": 1.0, |
| "sparse_reg": "l1", |
| "transformers_version": "5.14.1", |
| "use_2d_mlp": true, |
| "use_cross_device_negatives": false |
| } |
|
|
