| { |
| "_name_or_path": "ccdv/lsg-bart-base-4096", |
| "activation_dropout": 0.1, |
| "activation_function": "gelu", |
| "adaptive": true, |
| "add_bias_logits": false, |
| "add_final_layer_norm": false, |
| "architectures": [ |
| "LSGBartForConditionalGeneration" |
| ], |
| "attention_dropout": 0.1, |
| "auto_map": { |
| "AutoConfig": "modeling_lsg_bart.LSGBartConfig", |
| "AutoModel": "modeling_lsg_bart.LSGBartModel", |
| "AutoModelForCausalLM": "modeling_lsg_bart.LSGBartForCausalLM", |
| "AutoModelForQuestionAnswering": "modeling_lsg_bart.LSGBartForQuestionAnswering", |
| "AutoModelForSeq2SeqLM": "modeling_lsg_bart.LSGBartForConditionalGeneration", |
| "AutoModelForSequenceClassification": "modeling_lsg_bart.LSGBartForSequenceClassification" |
| }, |
| "base_model_prefix": "lsg", |
| "block_size": 128, |
| "bos_token_id": 0, |
| "classif_dropout": 0.1, |
| "classifier_dropout": 0.0, |
| "d_model": 768, |
| "decoder_attention_heads": 12, |
| "decoder_ffn_dim": 3072, |
| "decoder_layerdrop": 0.0, |
| "decoder_layers": 6, |
| "decoder_start_token_id": 2, |
| "dropout": 0.1, |
| "early_stopping": true, |
| "encoder_attention_heads": 12, |
| "encoder_ffn_dim": 3072, |
| "encoder_layerdrop": 0.0, |
| "encoder_layers": 6, |
| "eos_token_id": 2, |
| "forced_bos_token_id": 0, |
| "forced_eos_token_id": 2, |
| "gradient_checkpointing": false, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1", |
| "2": "LABEL_2" |
| }, |
| "init_std": 0.02, |
| "is_encoder_decoder": true, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_2": 2 |
| }, |
| "lsh_num_pre_rounds": 1, |
| "mask_first_token": false, |
| "max_position_embeddings": 4096, |
| "model_type": "bart", |
| "no_repeat_ngram_size": 3, |
| "normalize_before": false, |
| "normalize_embedding": true, |
| "num_beams": 4, |
| "num_global_tokens": 1, |
| "num_hidden_layers": 6, |
| "pad_token_id": 1, |
| "pass_global_tokens_to_decoder": true, |
| "pool_with_global": true, |
| "scale_embedding": false, |
| "sparse_block_size": 128, |
| "sparsity_factor": 2, |
| "sparsity_type": "norm", |
| "task_specific_params": { |
| "summarization": { |
| "length_penalty": 1.0, |
| "max_length": 128, |
| "min_length": 12, |
| "num_beams": 4 |
| }, |
| "summarization_cnn": { |
| "length_penalty": 2.0, |
| "max_length": 142, |
| "min_length": 56, |
| "num_beams": 4 |
| }, |
| "summarization_xsum": { |
| "length_penalty": 1.0, |
| "max_length": 62, |
| "min_length": 11, |
| "num_beams": 6 |
| } |
| }, |
| "torch_dtype": "float32", |
| "transformers_version": "4.19.2", |
| "use_cache": true, |
| "vocab_size": 50265 |
| } |
|
|
