| { | |
| "architectures": [ | |
| "DiffLLaMAForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 48, | |
| "hidden_act": "silu", | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2304, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "model_type": "diff_llama", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 16, | |
| "num_kv_heads": 4, | |
| "pad_token_id": 3, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "factor": 1.0, | |
| "type": "linear" | |
| }, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.45.2", | |
| "use_cache": true, | |
| "vocab_size": 32768 | |
| } | |