| { | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "architectures": [ | |
| "STLForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_stldec.STLConfig", | |
| "AutoModelForCausalLM": "modeling_stldec.STLForCausalLM" | |
| }, | |
| "bos_token_id": 2, | |
| "d_model": 1024, | |
| "decoder_attention_heads": 16, | |
| "decoder_ffn_dim": 4096, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 12, | |
| "decoder_start_token_id": 3, | |
| "decoder_vocab_size": 35, | |
| "dropout": 0.1, | |
| "dtype": "float32", | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 4096, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 12, | |
| "eos_token_id": 3, | |
| "forced_eos_token_id": 3, | |
| "init_std": 0.02, | |
| "is_decoder": true, | |
| "is_encoder_decoder": false, | |
| "max_position_embeddings": 1024, | |
| "model_type": "stldeconlyhard", | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "scale_embedding": false, | |
| "share_encoder_decoder_embeddings": true, | |
| "transformers_version": "4.57.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 35 | |
| } | |