|
{ |
|
"_name_or_path": "THUDM/glm-large-chinese", |
|
"architectures": [ |
|
"GLMModel" |
|
], |
|
"attention_dropout_prob": 0.1, |
|
"attention_scale": 1.0, |
|
"auto_map": { |
|
"AutoConfig": "configuration_glm.GLMConfig", |
|
"AutoModel": "modeling_glm.GLMModel", |
|
"AutoModelForSeq2SeqLM": "modeling_glm.GLMForConditionalGeneration", |
|
"AutoModelForMultipleChoice": "modeling_glm.GLMForMultipleChoice" |
|
}, |
|
"block_position_encoding": true, |
|
"checkpoint_activations": false, |
|
"checkpoint_num_layers": 1, |
|
"embedding_dropout_prob": 0.1, |
|
"hidden_size": 1024, |
|
"initializer_range": 0.02, |
|
"max_sequence_length": 1024, |
|
"model_type": "glm", |
|
"num_attention_heads": 16, |
|
"num_layers": 24, |
|
"output_dropout_prob": 0.1, |
|
"output_predict": true, |
|
"parallel_output": true, |
|
"pool_token": "cls", |
|
"relative_encoding": false, |
|
"spell_func": "lstm", |
|
"spell_length": null, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.23.1", |
|
"vocab_size": 50048 |
|
} |
|
|