| { | |
| "architectures": [ | |
| "DiffLlamaForQuestionAnswering" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 128000, | |
| "dtype": "float32", | |
| "eos_token_id": 128009, | |
| "head_dim": 8, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 32, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 37, | |
| "is_decoder": false, | |
| "lambda_std_dev": 0.1, | |
| "max_position_embeddings": 512, | |
| "model_type": "diffllama", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 128004, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.16.0.dev0", | |
| "type_vocab_size": 16, | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |