| { | |
| "_name_or_path": "BEE-spoke-data/ModernBERT2gpt2-700m-cfg2", | |
| "architectures": [ | |
| "EncoderDecoderModel" | |
| ], | |
| "bos_token_id": 50281, | |
| "decoder": { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "pszemraj/gpt2-OLMoTokenizer-random", | |
| "activation_function": "silu", | |
| "add_cross_attention": true, | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_pdrop": 0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 50279, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": 50279, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "embd_pdrop": 0.01, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 50279, | |
| "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": 0.01, | |
| "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_embd": 1024, | |
| "n_head": 16, | |
| "n_inner": 3584, | |
| "n_layer": 16, | |
| "n_positions": 4096, | |
| "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": 50283, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "reorder_and_upcast_attn": false, | |
| "repetition_penalty": 1.0, | |
| "resid_pdrop": 0.01, | |
| "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, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 50304 | |
| }, | |
| "decoder_start_token_id": 50279, | |
| "encoder": { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "answerdotai/ModernBERT-large", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "ModernBertForMaskedLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 50281, | |
| "chunk_size_feed_forward": 0, | |
| "classifier_activation": "gelu", | |
| "classifier_bias": false, | |
| "classifier_dropout": 0.0, | |
| "classifier_pooling": "mean", | |
| "cls_token_id": 50281, | |
| "cross_attention_hidden_size": null, | |
| "decoder_bias": true, | |
| "decoder_start_token_id": null, | |
| "deterministic_flash_attn": false, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "embedding_dropout": 0.0, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 50282, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "global_attn_every_n_layers": 3, | |
| "global_rope_theta": 160000.0, | |
| "gradient_checkpointing": false, | |
| "hidden_activation": "gelu", | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2624, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "length_penalty": 1.0, | |
| "local_attention": 128, | |
| "local_rope_theta": 10000.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 8192, | |
| "min_length": 0, | |
| "mlp_bias": false, | |
| "mlp_dropout": 0.0, | |
| "model_type": "modernbert", | |
| "no_repeat_ngram_size": 0, | |
| "norm_bias": false, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 28, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 50283, | |
| "position_embedding_type": "absolute", | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "reference_compile": false, | |
| "remove_invalid_values": false, | |
| "repad_logits_with_grad": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": 50282, | |
| "sparse_pred_ignore_index": -100, | |
| "sparse_prediction": false, | |
| "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, | |
| "vocab_size": 50368 | |
| }, | |
| "eos_token_id": 50279, | |
| "is_encoder_decoder": true, | |
| "model_type": "encoder-decoder", | |
| "pad_token_id": 50283, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.49.0.dev0" | |
| } | |