|
{ |
|
"return_dict": true, |
|
"output_hidden_states": false, |
|
"output_attentions": false, |
|
"torchscript": false, |
|
"torch_dtype": null, |
|
"use_bfloat16": false, |
|
"tf_legacy_loss": false, |
|
"pruned_heads": {}, |
|
"tie_word_embeddings": true, |
|
"chunk_size_feed_forward": 0, |
|
"is_encoder_decoder": True, |
|
"is_decoder": True, |
|
"cross_attention_hidden_size": null, |
|
"add_cross_attention": True, |
|
"tie_encoder_decoder": false, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"num_beams": 1, |
|
"num_beam_groups": 1, |
|
"diversity_penalty": 0.0, |
|
"temperature": 1.0, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"typical_p": 1.0, |
|
"repetition_penalty": 1.0, |
|
"length_penalty": 1.0, |
|
"no_repeat_ngram_size": 0, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"bad_words_ids": null, |
|
"num_return_sequences": 1, |
|
"output_scores": false, |
|
"return_dict_in_generate": True, |
|
"forced_bos_token_id": True, |
|
"forced_eos_token_id": True, |
|
"remove_invalid_values": false, |
|
"exponential_decay_length_penalty": null, |
|
"suppress_tokens": null, |
|
"begin_suppress_tokens": null, |
|
"architectures": ["AutoModelForCausalLM"], |
|
"finetuning_task": null, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
{ |
|
"tokenizer_class": "GPT2TokenizerFast", |
|
"prefix": "", |
|
"bos_token_id": 50256, |
|
"pad_token_id": 50257, |
|
"eos_token_id": 50256, |
|
"sep_token_id": 50259, |
|
"decoder_start_token_id": 50259, |
|
"task_specific_params": null, |
|
"problem_type": null, |
|
"_name_or_path": "Wonder-Griffin/Zeus", |
|
"transformers_version": "4.45.0.dev0", |
|
"vocab_size": 50000, |
|
"embed_dim": 512, |
|
"image_dim": 256, |
|
"audio_dim": 128, |
|
"reflection_dim": 512, |
|
"num_heads": 12, |
|
"num_experts": 4, |
|
"initializer_range": 0.02, |
|
"model_type": "Zeus" |
|
} |
|
|