| { |
| "_name_or_path": "", |
| "activation_dropout": 0.0, |
| "add_cross_attention": false, |
| "architectures": [ |
| "PantagruelUniForMaskedLM" |
| ], |
| "attention_dropout": 0.1, |
| "auto_map": { |
| "AutoConfig": "configuration_pantagruel_uni.PantagruelUniConfig", |
| "AutoModel": "modeling_pantagruel_uni.PantagruelUniModel", |
| "AutoModelForMaskedLM": "modeling_pantagruel_uni.PantagruelUniForMaskedLM", |
| "AutoModelForMultipleChoice": "modeling_pantagruel_uni.PantagruelUniForMultipleChoice", |
| "AutoModelForQuestionAnswering": "modeling_pantagruel_uni.PantagruelUniForQuestionAnswering", |
| "AutoModelForSequenceClassification": "modeling_pantagruel_uni.PantagruelUniForSequenceClassification", |
| "AutoModelForTokenClassification": "modeling_pantagruel_uni.PantagruelUniForTokenClassification" |
| }, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "classifier_dropout": null, |
| "clone_batch": 8, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "depth": 12, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dropout_input": 0.0, |
| "dtype": "float32", |
| "early_stopping": false, |
| "embed_dim": 768, |
| "encoder_dropout": 0.1, |
| "encoder_no_repeat_ngram_size": 0, |
| "end_drop_path_rate": 0.0, |
| "end_of_block_targets": false, |
| "eos_token_id": null, |
| "exponential_decay_length_penalty": null, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "hidden_size": 768, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "layer_norm_first": false, |
| "layerdrop": 0.0, |
| "length_penalty": 1.0, |
| "log_norms": true, |
| "max_length": 20, |
| "min_length": 0, |
| "mlp_ratio": 4.0, |
| "modalities": { |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "architectures": null, |
| "audio": { |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "add_masks": false, |
| "alibi_max_pos": null, |
| "alibi_scale": 1.0, |
| "architectures": null, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "conv_pos_depth": 5, |
| "conv_pos_groups": 16, |
| "conv_pos_pre_ln": false, |
| "conv_pos_width": 95, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": null, |
| "early_stopping": false, |
| "encoder_no_repeat_ngram_size": 0, |
| "encoder_zero_mask": true, |
| "end_drop_path_rate": 0.0, |
| "eos_token_id": null, |
| "exponential_decay_length_penalty": null, |
| "extractor_mode": "layer_norm", |
| "feature_encoder_spec": "[(512, 10, 5)] + [(512, 3, 2)] * 4 + [(512,2,2)] + [(512,2,2)]", |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "init_extra_token_zero": true, |
| "inverse_mask": false, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "keep_masked_pct": 0.0, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "learned_alibi": false, |
| "learned_alibi_scale": false, |
| "learned_alibi_scale_per_head": false, |
| "learned_alibi_scale_per_layer": false, |
| "length_penalty": 1.0, |
| "local_grad_mult": 1.0, |
| "mask_channel_length": 64, |
| "mask_channel_prob": 0.0, |
| "mask_dropout": 0.0, |
| "mask_length": 5, |
| "mask_noise_std": 0.01, |
| "mask_prob": 0.7, |
| "mask_prob_adjust": 0.0, |
| "mask_prob_min": null, |
| "max_length": 20, |
| "min_length": 0, |
| "model_depth": 12, |
| "model_type": "", |
| "no_repeat_ngram_size": 0, |
| "num_alibi_heads": 12, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_extra_tokens": 0, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": null, |
| "prefix": null, |
| "prenet_depth": 4, |
| "prenet_dropout": 0.0, |
| "prenet_layerdrop": 0.0, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "remove_invalid_values": false, |
| "remove_masks": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "sep_token_id": null, |
| "start_drop_path_rate": 0.0, |
| "suppress_tokens": null, |
| "task_specific_params": null, |
| "temperature": 1.0, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": true, |
| "tokenizer_class": null, |
| "top_k": 50, |
| "top_p": 1.0, |
| "torchscript": false, |
| "type": "AUDIO", |
| "typical_p": 1.0, |
| "use_alibi_encoder": false |
| }, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": null, |
| "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, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "min_length": 0, |
| "model_type": "", |
| "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": null, |
| "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, |
| "text": { |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "add_masks": false, |
| "alibi_max_pos": null, |
| "alibi_scale": 1.0, |
| "architectures": null, |
| "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, |
| "dropout": 0.1, |
| "dtype": null, |
| "early_stopping": false, |
| "encoder_no_repeat_ngram_size": 0, |
| "encoder_zero_mask": true, |
| "end_drop_path_rate": 0.0, |
| "eos_token_id": 2, |
| "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" |
| }, |
| "init_extra_token_zero": true, |
| "inverse_mask": false, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "keep_masked_pct": 0.0, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "layernorm_embedding": true, |
| "learned_alibi": false, |
| "learned_alibi_scale": true, |
| "learned_alibi_scale_per_head": true, |
| "learned_alibi_scale_per_layer": false, |
| "learned_pos": true, |
| "length_penalty": 1.0, |
| "local_grad_mult": 1.0, |
| "mask_channel_length": 64, |
| "mask_channel_prob": 0.0, |
| "mask_dropout": 0.0, |
| "mask_length": 3, |
| "mask_noise_std": 0.01, |
| "mask_prob": 0.6, |
| "mask_prob_adjust": 0.0, |
| "mask_prob_min": null, |
| "max_length": 20, |
| "max_source_positions": 512, |
| "min_length": 0, |
| "model_depth": 12, |
| "model_type": "", |
| "no_repeat_ngram_size": 0, |
| "no_scale_embedding": true, |
| "no_token_positional_embeddings": false, |
| "num_alibi_heads": 12, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_extra_tokens": 0, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": 1, |
| "prefix": null, |
| "prenet_depth": 0, |
| "prenet_dropout": 0.0, |
| "prenet_layerdrop": 0.0, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "remove_invalid_values": false, |
| "remove_masks": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "sep_token_id": null, |
| "start_drop_path_rate": 0.0, |
| "suppress_tokens": null, |
| "task_specific_params": null, |
| "temperature": 1.0, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": true, |
| "tokenizer_class": null, |
| "top_k": 50, |
| "top_p": 1.0, |
| "torchscript": false, |
| "type": "TEXT", |
| "typical_p": 1.0, |
| "unk_token_id": 3, |
| "use_alibi_encoder": true, |
| "vocab_size": 50368 |
| }, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": true, |
| "tokenizer_class": null, |
| "top_k": 50, |
| "top_p": 1.0, |
| "torchscript": false, |
| "typical_p": 1.0 |
| }, |
| "model_type": "pantagruel_uni", |
| "n_layers": 12, |
| "no_repeat_ngram_size": 0, |
| "norm_affine": true, |
| "norm_eps": 1e-05, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_heads": 12, |
| "num_hidden_layers": 12, |
| "num_layers": 12, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": null, |
| "post_mlp_drop": 0.1, |
| "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, |
| "start_drop_path_rate": 0.0, |
| "supported_modality": "TEXT", |
| "suppress_tokens": null, |
| "task_specific_params": null, |
| "temperature": 1.0, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": true, |
| "tokenizer_class": null, |
| "top_k": 50, |
| "top_p": 1.0, |
| "torchscript": false, |
| "transformers_version": "4.57.0.dev0", |
| "typical_p": 1.0 |
| } |
|
|
