|
{ |
|
"module": "keras_nlp.models.gpt2.gpt2_causal_lm", |
|
"class_name": "GPT2CausalLM", |
|
"config": { |
|
"backbone": { |
|
"module": "keras_nlp.models.gpt2.gpt2_backbone", |
|
"class_name": "GPT2Backbone", |
|
"config": { |
|
"name": "gpt2_backbone", |
|
"trainable": true, |
|
"vocabulary_size": 50257, |
|
"num_layers": 12, |
|
"num_heads": 12, |
|
"hidden_dim": 768, |
|
"intermediate_dim": 3072, |
|
"dropout": 0.1, |
|
"max_sequence_length": 1024 |
|
}, |
|
"registered_name": "keras_nlp>GPT2Backbone" |
|
}, |
|
"preprocessor": { |
|
"module": "keras_nlp.models.gpt2.gpt2_causal_lm_preprocessor", |
|
"class_name": "GPT2CausalLMPreprocessor", |
|
"config": { |
|
"name": "gpt2_causal_lm_preprocessor", |
|
"trainable": true, |
|
"dtype": "float32", |
|
"tokenizer": { |
|
"module": "keras_nlp.models.gpt2.gpt2_tokenizer", |
|
"class_name": "GPT2Tokenizer", |
|
"config": { |
|
"name": "gpt2_tokenizer", |
|
"trainable": true, |
|
"dtype": "int32", |
|
"sequence_length": null, |
|
"add_prefix_space": false |
|
}, |
|
"registered_name": "keras_nlp>GPT2Tokenizer" |
|
}, |
|
"sequence_length": 1024, |
|
"add_start_token": true, |
|
"add_end_token": true |
|
}, |
|
"registered_name": "keras_nlp>GPT2CausalLMPreprocessor" |
|
}, |
|
"name": "gpt2_causal_lm" |
|
}, |
|
"registered_name": "keras_nlp>GPT2CausalLM" |
|
} |