|
{ |
|
"activation_function": "gelu_new", |
|
"architectures": [ |
|
"GPTJForCausalLM" |
|
], |
|
"attention_dropout": 0, |
|
"attention_layers": ["global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global"], |
|
"attention_types": [ |
|
[ |
|
[ |
|
"global" |
|
], |
|
28 |
|
] |
|
], |
|
"bos_token_id": 50256, |
|
"embed_dropout": 0, |
|
"eos_token_id": 50256, |
|
"gradient_checkpointing": false, |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": null, |
|
"jax": true, |
|
"layer_norm_epsilon": 1e-05, |
|
"max_position_embeddings": 2048, |
|
"model_type": "gptj", |
|
"num_heads": 16, |
|
"num_layers": 28, |
|
"resid_dropout": 0, |
|
"rotary": true, |
|
"rotary_dim": 64, |
|
"summary_activation": null, |
|
"summary_first_dropout": 0.1, |
|
"summary_proj_to_labels": true, |
|
"summary_type": "cls_index", |
|
"summary_use_proj": true, |
|
"transformers_version": "4.10.0.dev0", |
|
"use_cache": true, |
|
"vocab_size": 50400, |
|
"window_size": 256, |
|
"tokenizer_class": "GPT2Tokenizer", |
|
"task_specific_params": { |
|
"text-generation": { |
|
"do_sample": true, |
|
"temperature": 1.0, |
|
"max_length": 50 |
|
} |
|
} |
|
} |